Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 809 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2923. Min Act: -0.1700

Data Index: 240463 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2766. Min Act: -0.1700

Data Index: 901799 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1134718 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2452. Min Act: -0.1700

Data Index: 1150557 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1980. Min Act: -0.1700

Data Index: 1235305 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2137. Min Act: -0.1700

Data Index: 166251 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1216421 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2137. Min Act: -0.1700

Data Index: 44364 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1665. Min Act: -0.1700

Data Index: 571164 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1665. Min Act: -0.1700

Data Index: 724208 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1350. Min Act: -0.1700

Data Index: 1041510 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1508. Min Act: -0.1700

Data Index: 588477 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1665. Min Act: -0.1700

Data Index: 1194383 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1078553 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1350. Min Act: -0.1700

Data Index: 596237 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1193. Min Act: -0.1700

Data Index: 468152 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1350. Min Act: -0.1700

Data Index: 1139149 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1193. Min Act: -0.1700

Data Index: 295383 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1193. Min Act: -0.1700

Data Index: 893822 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0877. Min Act: -0.1700

Data Index: 738 (C4 (Web Text))

Max Activating Token Index: 170