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

Dataset: Open Web Text

Neuron 907 in Layer 5

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: 5.5555. Min Range: -5.5555

Max Act: 5.5555. Min Act: -0.1700

Data Index: 8396420 (Open Web Text)

Max Activating Token Index: 262

Text #1

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.5114. Min Act: -0.1700

Data Index: 1746591 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.5292. Min Act: -0.1700

Data Index: 1445086 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.4510. Min Act: -0.1700

Data Index: 6564669 (Open Web Text)

Max Activating Token Index: 1002

Text #4

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3848. Min Act: -0.1700

Data Index: 1759166 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3871. Min Act: -0.1700

Data Index: 396801 (Open Web Text)

Max Activating Token Index: 705

Text #6

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3515. Min Act: -0.1700

Data Index: 6498189 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3586. Min Act: -0.1700

Data Index: 1539160 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3467. Min Act: -0.1700

Data Index: 7660230 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3325. Min Act: -0.1700

Data Index: 1587493 (Open Web Text)

Max Activating Token Index: 934

Text #10

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3163. Min Act: -0.1700

Data Index: 3485907 (Open Web Text)

Max Activating Token Index: 560

Text #11

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3041. Min Act: -0.1700

Data Index: 2202760 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3016. Min Act: -0.1700

Data Index: 595184 (Open Web Text)

Max Activating Token Index: 233

Text #13

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3278. Min Act: -0.1700

Data Index: 6654271 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.3329. Min Act: -0.1700

Data Index: 2779624 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.2753. Min Act: -0.1700

Data Index: 652270 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.2783. Min Act: -0.1700

Data Index: 7319533 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.2830. Min Act: -0.1700

Data Index: 2750210 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.2789. Min Act: -0.1700

Data Index: 1989601 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 5.5555. Min Range: -5.5555

Max Act: 5.2376. Min Act: -0.1700

Data Index: 3690728 (Open Web Text)

Max Activating Token Index: 501