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

Dataset: Open Web Text

Neuron 2113 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: 1.7899. Min Range: -1.7899

Max Act: 1.7899. Min Act: -0.1700

Data Index: 918497 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.7568. Min Act: -0.1700

Data Index: 7314589 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.7796. Min Act: -0.1700

Data Index: 1112578 (Open Web Text)

Max Activating Token Index: 790

Text #3

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.7271. Min Act: -0.1700

Data Index: 3780142 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6995. Min Act: -0.1700

Data Index: 6469022 (Open Web Text)

Max Activating Token Index: 979

Text #5

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6825. Min Act: -0.1700

Data Index: 1018876 (Open Web Text)

Max Activating Token Index: 685

Text #6

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6772. Min Act: -0.1700

Data Index: 1262505 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6888. Min Act: -0.1700

Data Index: 2737033 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6727. Min Act: -0.1700

Data Index: 5540850 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6434. Min Act: -0.1700

Data Index: 7436695 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6393. Min Act: -0.1700

Data Index: 7276460 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6290. Min Act: -0.1700

Data Index: 1930108 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6374. Min Act: -0.1700

Data Index: 1895588 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6343. Min Act: -0.1700

Data Index: 1680041 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6384. Min Act: -0.1700

Data Index: 6514213 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6310. Min Act: -0.1700

Data Index: 6323386 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6389. Min Act: -0.1700

Data Index: 2998998 (Open Web Text)

Max Activating Token Index: 722

Text #17

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6288. Min Act: -0.1700

Data Index: 8653290 (Open Web Text)

Max Activating Token Index: 246

Text #18

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6257. Min Act: -0.1700

Data Index: 2430159 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 1.7899. Min Range: -1.7899

Max Act: 1.6314. Min Act: -0.1700

Data Index: 6466991 (Open Web Text)

Max Activating Token Index: 243