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

Dataset: Open Web Text

Neuron 2536 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: 4.8497. Min Range: -4.8497

Max Act: 4.8497. Min Act: -0.1700

Data Index: 929508 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.8194. Min Act: -0.1700

Data Index: 6345284 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.8226. Min Act: -0.1700

Data Index: 1724012 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7667. Min Act: -0.1700

Data Index: 6860948 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7769. Min Act: -0.1700

Data Index: 3167236 (Open Web Text)

Max Activating Token Index: 160

Text #5

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7405. Min Act: -0.1700

Data Index: 2788833 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7340. Min Act: -0.1700

Data Index: 3960550 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7358. Min Act: -0.1700

Data Index: 6077593 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7281. Min Act: -0.1700

Data Index: 2585923 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7392. Min Act: -0.1700

Data Index: 3258828 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7284. Min Act: -0.1700

Data Index: 6411746 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.6811. Min Act: -0.1700

Data Index: 505282 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.6778. Min Act: -0.1700

Data Index: 7155544 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7234. Min Act: -0.1700

Data Index: 4853226 (Open Web Text)

Max Activating Token Index: 426

Text #14

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7088. Min Act: -0.1700

Data Index: 491743 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7091. Min Act: -0.1700

Data Index: 7418556 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.7030. Min Act: -0.1700

Data Index: 1592549 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.6492. Min Act: -0.1700

Data Index: 4608545 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.6645. Min Act: -0.1700

Data Index: 4913220 (Open Web Text)

Max Activating Token Index: 524

Text #19

Max Range: 4.8497. Min Range: -4.8497

Max Act: 4.6565. Min Act: -0.1700

Data Index: 1885300 (Open Web Text)

Max Activating Token Index: 336