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

Dataset: Open Web Text

Neuron 586 in Layer 2

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: 1.9604. Min Range: -1.9604

Max Act: 1.9604. Min Act: -0.1700

Data Index: 4209192 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9092. Min Act: -0.1700

Data Index: 3642611 (Open Web Text)

Max Activating Token Index: 81

Text #2

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9187. Min Act: -0.1700

Data Index: 3793051 (Open Web Text)

Max Activating Token Index: 503

Text #3

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8875. Min Act: -0.1700

Data Index: 2021594 (Open Web Text)

Max Activating Token Index: 969

Text #4

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9003. Min Act: -0.1700

Data Index: 2382189 (Open Web Text)

Max Activating Token Index: 470

Text #5

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9040. Min Act: -0.1700

Data Index: 8050432 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8900. Min Act: -0.1700

Data Index: 6390772 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8799. Min Act: -0.1700

Data Index: 7328463 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8860. Min Act: -0.1700

Data Index: 3464231 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8677. Min Act: -0.1700

Data Index: 6743523 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8440. Min Act: -0.1700

Data Index: 8635675 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8612. Min Act: -0.1700

Data Index: 4074472 (Open Web Text)

Max Activating Token Index: 266

Text #12

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8462. Min Act: -0.1700

Data Index: 6710785 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8519. Min Act: -0.1700

Data Index: 6257463 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8527. Min Act: -0.1700

Data Index: 4115224 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8433. Min Act: -0.1700

Data Index: 7033058 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8516. Min Act: -0.1700

Data Index: 4449937 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8402. Min Act: -0.1700

Data Index: 8391514 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8333. Min Act: -0.1700

Data Index: 7159529 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.8402. Min Act: -0.1700

Data Index: 7023900 (Open Web Text)

Max Activating Token Index: 341