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

Dataset: Open Web Text

Neuron 866 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: 3.7282. Min Range: -3.7282

Max Act: 3.7198. Min Act: -0.1700

Data Index: 4495071 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.7282. Min Act: -0.1700

Data Index: 4717636 (Open Web Text)

Max Activating Token Index: 456

Text #2

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6834. Min Act: -0.1700

Data Index: 459142 (Open Web Text)

Max Activating Token Index: 362

Text #3

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5991. Min Act: -0.1700

Data Index: 8114396 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6724. Min Act: -0.1700

Data Index: 5259105 (Open Web Text)

Max Activating Token Index: 793

Text #5

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6797. Min Act: -0.1700

Data Index: 797763 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6733. Min Act: -0.1700

Data Index: 1859489 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6022. Min Act: -0.1700

Data Index: 236412 (Open Web Text)

Max Activating Token Index: 809

Text #8

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6222. Min Act: -0.1700

Data Index: 4875728 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6131. Min Act: -0.1700

Data Index: 6939732 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6060. Min Act: -0.1700

Data Index: 5223389 (Open Web Text)

Max Activating Token Index: 910

Text #11

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5464. Min Act: -0.1700

Data Index: 2793929 (Open Web Text)

Max Activating Token Index: 899

Text #12

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5430. Min Act: -0.1700

Data Index: 5267232 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5394. Min Act: -0.1700

Data Index: 8539652 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5742. Min Act: -0.1700

Data Index: 3553527 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.4978. Min Act: -0.1700

Data Index: 2536803 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5199. Min Act: -0.1700

Data Index: 7289010 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5556. Min Act: -0.1700

Data Index: 4075148 (Open Web Text)

Max Activating Token Index: 421

Text #18

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5082. Min Act: -0.1700

Data Index: 2827292 (Open Web Text)

Max Activating Token Index: 105

Text #19

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5117. Min Act: -0.1700

Data Index: 6663222 (Open Web Text)

Max Activating Token Index: 339