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

Dataset: Open Web Text

Neuron 40 in Layer 3

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: 4.1212. Min Range: -4.1212

Max Act: 4.1212. Min Act: -0.1700

Data Index: 4505432 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0654. Min Act: -0.1700

Data Index: 4579828 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0393. Min Act: -0.1700

Data Index: 5639575 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0213. Min Act: -0.1700

Data Index: 1747778 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0413. Min Act: -0.1700

Data Index: 1907068 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0384. Min Act: -0.1700

Data Index: 5968975 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0413. Min Act: -0.1700

Data Index: 140111 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 4.1212. Min Range: -4.1212

Max Act: 4.0159. Min Act: -0.1700

Data Index: 5890156 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9814. Min Act: -0.1700

Data Index: 6676636 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9773. Min Act: -0.1700

Data Index: 6295269 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9553. Min Act: -0.1700

Data Index: 2432773 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9591. Min Act: -0.1700

Data Index: 8433914 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9751. Min Act: -0.1700

Data Index: 271220 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9689. Min Act: -0.1700

Data Index: 5133422 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9701. Min Act: -0.1700

Data Index: 4596317 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9703. Min Act: -0.1700

Data Index: 4573038 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9776. Min Act: -0.1700

Data Index: 4416252 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9715. Min Act: -0.1700

Data Index: 726485 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9260. Min Act: -0.1700

Data Index: 3754660 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.1212. Min Range: -4.1212

Max Act: 3.9519. Min Act: -0.1700

Data Index: 1734840 (Open Web Text)

Max Activating Token Index: 776