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

Dataset: Open Web Text

Neuron 551 in Layer 2

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: 5.4124. Min Range: -5.4124

Max Act: 5.4124. Min Act: -0.1700

Data Index: 7685222 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.4005. Min Act: -0.1700

Data Index: 1631063 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3790. Min Act: -0.1700

Data Index: 8055789 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3666. Min Act: -0.1700

Data Index: 2745872 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3217. Min Act: -0.1700

Data Index: 5872316 (Open Web Text)

Max Activating Token Index: 732

Text #5

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3105. Min Act: -0.1700

Data Index: 3390171 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2782. Min Act: -0.1700

Data Index: 3590242 (Open Web Text)

Max Activating Token Index: 754

Text #7

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3295. Min Act: -0.1700

Data Index: 2060231 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.3565. Min Act: -0.1700

Data Index: 4520928 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2782. Min Act: -0.1700

Data Index: 38860 (Open Web Text)

Max Activating Token Index: 440

Text #10

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2881. Min Act: -0.1700

Data Index: 5503863 (Open Web Text)

Max Activating Token Index: 982

Text #11

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2569. Min Act: -0.1700

Data Index: 3961418 (Open Web Text)

Max Activating Token Index: 991

Text #12

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2549. Min Act: -0.1700

Data Index: 1395789 (Open Web Text)

Max Activating Token Index: 837

Text #13

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2235. Min Act: -0.1699

Data Index: 5976900 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2205. Min Act: -0.1700

Data Index: 4597116 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2176. Min Act: -0.1700

Data Index: 3345676 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2548. Min Act: -0.1700

Data Index: 6904498 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2127. Min Act: -0.1700

Data Index: 4913419 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2242. Min Act: -0.1700

Data Index: 522338 (Open Web Text)

Max Activating Token Index: 371

Text #19

Max Range: 5.4124. Min Range: -5.4124

Max Act: 5.2414. Min Act: -0.1700

Data Index: 7158277 (Open Web Text)

Max Activating Token Index: 752