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

Dataset: Open Web Text

Neuron 929 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: 4.3136. Min Range: -4.3136

Max Act: 4.3136. Min Act: -0.1700

Data Index: 5199107 (Open Web Text)

Max Activating Token Index: 767

Text #1

Max Range: 4.3136. Min Range: -4.3136

Max Act: 4.1236. Min Act: -0.1700

Data Index: 1459136 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 4.3136. Min Range: -4.3136

Max Act: 4.0113. Min Act: -0.1700

Data Index: 5726190 (Open Web Text)

Max Activating Token Index: 665

Text #3

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9802. Min Act: -0.1700

Data Index: 7030968 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9619. Min Act: -0.1700

Data Index: 3943846 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9494. Min Act: -0.1700

Data Index: 1277091 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9442. Min Act: -0.1700

Data Index: 339121 (Open Web Text)

Max Activating Token Index: 809

Text #7

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9349. Min Act: -0.1700

Data Index: 987709 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8973. Min Act: -0.1700

Data Index: 5997152 (Open Web Text)

Max Activating Token Index: 78

Text #9

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8803. Min Act: -0.1700

Data Index: 6430323 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8957. Min Act: -0.1700

Data Index: 6623458 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8996. Min Act: -0.1700

Data Index: 2608842 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9236. Min Act: -0.1700

Data Index: 1838225 (Open Web Text)

Max Activating Token Index: 612

Text #13

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1978421 (Open Web Text)

Max Activating Token Index: 617

Text #14

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9166. Min Act: -0.1700

Data Index: 2744498 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8891. Min Act: -0.1700

Data Index: 2241848 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8948. Min Act: -0.1700

Data Index: 1726291 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8707. Min Act: -0.1700

Data Index: 5912573 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.9186. Min Act: -0.1700

Data Index: 810735 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 4.3136. Min Range: -4.3136

Max Act: 3.8968. Min Act: -0.1700

Data Index: 7772033 (Open Web Text)

Max Activating Token Index: 452