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

Dataset: Open Web Text

Neuron 2139 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: 3.0425. Min Range: -3.0425

Max Act: 3.0425. Min Act: -0.1700

Data Index: 7531462 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.9252. Min Act: -0.1700

Data Index: 876833 (Open Web Text)

Max Activating Token Index: 588

Text #2

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.9317. Min Act: -0.1700

Data Index: 6351697 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.9060. Min Act: -0.1700

Data Index: 4825917 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.8363. Min Act: -0.1700

Data Index: 5427481 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7883. Min Act: -0.1700

Data Index: 5695822 (Open Web Text)

Max Activating Token Index: 809

Text #6

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7643. Min Act: -0.1700

Data Index: 685788 (Open Web Text)

Max Activating Token Index: 636

Text #7

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7631. Min Act: -0.1700

Data Index: 8256493 (Open Web Text)

Max Activating Token Index: 232

Text #8

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7622. Min Act: -0.1700

Data Index: 1275163 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7084. Min Act: -0.1700

Data Index: 7473082 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7064. Min Act: -0.1700

Data Index: 4953459 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7165. Min Act: -0.1700

Data Index: 4188215 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.6825. Min Act: -0.1700

Data Index: 8728277 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7252. Min Act: -0.1700

Data Index: 1181686 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7097. Min Act: -0.1700

Data Index: 7256728 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.6895. Min Act: -0.1700

Data Index: 5651278 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.7036. Min Act: -0.1700

Data Index: 5705240 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.6992. Min Act: -0.1700

Data Index: 791024 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.6844. Min Act: -0.1700

Data Index: 3906852 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 3.0425. Min Range: -3.0425

Max Act: 2.6995. Min Act: -0.1700

Data Index: 1242608 (Open Web Text)

Max Activating Token Index: 43