Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.4934. Min Act: -0.1700

Data Index: 1224402 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1999028 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.4278. Min Act: -0.1700

Data Index: 4845885 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.4032. Min Act: -0.1700

Data Index: 7264253 (Open Web Text)

Max Activating Token Index: 195

Text #4

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.4183. Min Act: -0.1700

Data Index: 1875386 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3930. Min Act: -0.1700

Data Index: 1372231 (Open Web Text)

Max Activating Token Index: 499

Text #6

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3933. Min Act: -0.1700

Data Index: 6878060 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3817. Min Act: -0.1700

Data Index: 1197715 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3689. Min Act: -0.1700

Data Index: 2489976 (Open Web Text)

Max Activating Token Index: 284

Text #9

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3744. Min Act: -0.1700

Data Index: 1372230 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3480. Min Act: -0.1700

Data Index: 1372229 (Open Web Text)

Max Activating Token Index: 566

Text #11

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3471. Min Act: -0.1700

Data Index: 4455262 (Open Web Text)

Max Activating Token Index: 838

Text #12

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3574. Min Act: -0.1700

Data Index: 8763901 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3355. Min Act: -0.1700

Data Index: 4380021 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3315. Min Act: -0.1700

Data Index: 3814916 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3173. Min Act: -0.1700

Data Index: 6878053 (Open Web Text)

Max Activating Token Index: 585

Text #16

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3111. Min Act: -0.1700

Data Index: 1713459 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3191. Min Act: -0.1700

Data Index: 3404227 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.2989. Min Act: -0.1700

Data Index: 662530 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.4934. Min Range: -3.4934

Max Act: 3.3320. Min Act: -0.1700

Data Index: 4933439 (Open Web Text)

Max Activating Token Index: 602