< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6350 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.5129. Min Act: -0.1700

Data Index: 3721891 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.5129. Min Act: -0.1700

Data Index: 893095 (Open Web Text)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.3879. Min Act: -0.1700

Data Index: 5451705 (Open Web Text)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.3879. Min Act: -0.1700

Data Index: 6740193 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.2629. Min Act: -0.1700

Data Index: 4833335 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.1379. Min Act: -0.1700

Data Index: 948217 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.1379. Min Act: -0.1700

Data Index: 2263481 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.1379. Min Act: -0.1700

Data Index: 7527335 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.1379. Min Act: -0.1700

Data Index: 3370852 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.0129. Min Act: -0.1700

Data Index: 2263493 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.0129. Min Act: -0.1700

Data Index: 5011144 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.8879. Min Act: -0.1700

Data Index: 7549215 (Open Web Text)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.0129. Min Act: -0.1700

Data Index: 127179 (Open Web Text)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.0129. Min Act: -0.1700

Data Index: 347207 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 23.5129. Min Range: -23.5129

Max Act: 23.0129. Min Act: -0.1700

Data Index: 2263472 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.8879. Min Act: -0.1700

Data Index: 948221 (Open Web Text)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.8879. Min Act: -0.1700

Data Index: 627664 (Open Web Text)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.8879. Min Act: -0.1700

Data Index: 3307045 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.8879. Min Act: -0.1700

Data Index: 5580345 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 23.5129. Min Range: -23.5129

Max Act: 22.7629. Min Act: -0.1700

Data Index: 5261678 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #19