< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 25 in Layer 42

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.9641. Min Act: -0.1700

Data Index: 8734187 (Open Web Text)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.9641. Min Act: -0.1700

Data Index: 8693157 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.7141. Min Act: -0.1700

Data Index: 3503597 (Open Web Text)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.6516. Min Act: -0.1700

Data Index: 4238999 (Open Web Text)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.5891. Min Act: -0.1700

Data Index: 8647130 (Open Web Text)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.7141. Min Act: -0.1700

Data Index: 5828118 (Open Web Text)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.6516. Min Act: -0.1700

Data Index: 6078909 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.5266. Min Act: -0.1700

Data Index: 30272 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4641. Min Act: -0.1700

Data Index: 5985682 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.5266. Min Act: -0.1700

Data Index: 5864187 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4641. Min Act: -0.1700

Data Index: 5097891 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 1221690 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 907914 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 4086999 (Open Web Text)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 4977536 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 8457428 (Open Web Text)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 7366310 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 7138495 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 6291600 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.9641. Min Range: -10.9641

Max Act: 10.4016. Min Act: -0.1700

Data Index: 6286635 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #19