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

Dataset: Open Web Text

Neuron 2942 in Layer 6

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: 4.9124. Min Range: -4.9124

Max Act: 4.9124. Min Act: -0.1700

Data Index: 8420557 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.8680. Min Act: -0.1700

Data Index: 5142784 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.8512. Min Act: -0.1700

Data Index: 7711818 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7687. Min Act: -0.1700

Data Index: 116179 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.8457. Min Act: -0.1700

Data Index: 1115623 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7180. Min Act: -0.1700

Data Index: 2662821 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7766. Min Act: -0.1700

Data Index: 2035773 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7914. Min Act: -0.1700

Data Index: 6801023 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.6754. Min Act: -0.1700

Data Index: 3106987 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.6548. Min Act: -0.1700

Data Index: 8589162 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.6209. Min Act: -0.1700

Data Index: 3619982 (Open Web Text)

Max Activating Token Index: 834

Text #11

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5844. Min Act: -0.1700

Data Index: 3439423 (Open Web Text)

Max Activating Token Index: 977

Text #12

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.6010. Min Act: -0.1700

Data Index: 3805468 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5656. Min Act: -0.1700

Data Index: 4005113 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5992. Min Act: -0.1700

Data Index: 1418813 (Open Web Text)

Max Activating Token Index: 824

Text #15

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.6182. Min Act: -0.1700

Data Index: 8177244 (Open Web Text)

Max Activating Token Index: 801

Text #16

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5224. Min Act: -0.1700

Data Index: 142810 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5559. Min Act: -0.1700

Data Index: 3770841 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5218. Min Act: -0.1700

Data Index: 3761648 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.5384. Min Act: -0.1700

Data Index: 743694 (Open Web Text)

Max Activating Token Index: 921