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

Dataset: Open Web Text

Neuron 36 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: 4.8585. Min Range: -4.8585

Max Act: 4.8585. Min Act: -0.1700

Data Index: 4436680 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7409. Min Act: -0.1700

Data Index: 3144880 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7273. Min Act: -0.1700

Data Index: 1044305 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.6414. Min Act: -0.1700

Data Index: 2907682 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5959. Min Act: -0.1700

Data Index: 4089050 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5924. Min Act: -0.1700

Data Index: 1671373 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5564. Min Act: -0.1700

Data Index: 8604647 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5544. Min Act: -0.1700

Data Index: 737379 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5509. Min Act: -0.1700

Data Index: 3464211 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5479. Min Act: -0.1700

Data Index: 8830631 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5649. Min Act: -0.1700

Data Index: 4122302 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5334. Min Act: -0.1700

Data Index: 6400387 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5217. Min Act: -0.1700

Data Index: 1837592 (Open Web Text)

Max Activating Token Index: 639

Text #13

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5314. Min Act: -0.1700

Data Index: 8377882 (Open Web Text)

Max Activating Token Index: 238

Text #14

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.5200. Min Act: -0.1700

Data Index: 5636336 (Open Web Text)

Max Activating Token Index: 828

Text #15

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.4970. Min Act: -0.1700

Data Index: 7126729 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.4444. Min Act: -0.1700

Data Index: 8351086 (Open Web Text)

Max Activating Token Index: 298

Text #17

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.4970. Min Act: -0.1700

Data Index: 4445695 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.4724. Min Act: -0.1700

Data Index: 3607612 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.4635. Min Act: -0.1700

Data Index: 7030973 (Open Web Text)

Max Activating Token Index: 142