< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6376 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.5340. Min Act: -0.1700

Data Index: 2065632 (Open Web Text)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.5340. Min Act: -0.1700

Data Index: 7977919 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.5027. Min Act: -0.1700

Data Index: 3341676 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.4402. Min Act: -0.1700

Data Index: 8299713 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.4402. Min Act: -0.1700

Data Index: 5981629 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.4090. Min Act: -0.1700

Data Index: 3668607 (Open Web Text)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3777. Min Act: -0.1700

Data Index: 1481960 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3465. Min Act: -0.1700

Data Index: 7015011 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3465. Min Act: -0.1700

Data Index: 2438820 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3465. Min Act: -0.1700

Data Index: 2528303 (Open Web Text)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3465. Min Act: -0.1700

Data Index: 2167531 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3465. Min Act: -0.1700

Data Index: 1381962 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3152. Min Act: -0.1700

Data Index: 2694428 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.2840. Min Act: -0.1700

Data Index: 6343208 (Open Web Text)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3152. Min Act: -0.1700

Data Index: 6154089 (Open Web Text)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3152. Min Act: -0.1700

Data Index: 3196522 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.2840. Min Act: -0.1700

Data Index: 4637750 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3152. Min Act: -0.1700

Data Index: 3019702 (Open Web Text)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.3152. Min Act: -0.1700

Data Index: 4765695 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.5340. Min Range: -5.5340

Max Act: 5.2840. Min Act: -0.1700

Data Index: 3006229 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #19