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

Dataset: Open Web Text

Neuron 2134 in Layer 1

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: 1.9939. Min Range: -1.9939

Max Act: 1.9939. Min Act: -0.1693

Data Index: 5235999 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9720. Min Act: -0.1700

Data Index: 1341896 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9787. Min Act: -0.1700

Data Index: 5564593 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9782. Min Act: -0.1700

Data Index: 4656863 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9686. Min Act: -0.1700

Data Index: 1060659 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9608. Min Act: -0.1700

Data Index: 23699 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9623. Min Act: -0.1696

Data Index: 7394984 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9570. Min Act: -0.1700

Data Index: 7030859 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9608. Min Act: -0.1695

Data Index: 3030727 (Open Web Text)

Max Activating Token Index: 404

Text #9

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9468. Min Act: -0.1700

Data Index: 7585172 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9523. Min Act: -0.1696

Data Index: 3480727 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9458. Min Act: -0.1700

Data Index: 6477705 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9427. Min Act: -0.1700

Data Index: 6219599 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9355. Min Act: -0.1700

Data Index: 5321834 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9192. Min Act: -0.1700

Data Index: 2997512 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9222. Min Act: -0.1700

Data Index: 4387674 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9233. Min Act: -0.1700

Data Index: 5368515 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9208. Min Act: -0.1700

Data Index: 4344350 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9217. Min Act: -0.1699

Data Index: 3735216 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9077. Min Act: -0.1700

Data Index: 104292 (Open Web Text)

Max Activating Token Index: 28