Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7793. Min Act: -0.0001

Data Index: 53109 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7793. Min Act: -0.0001

Data Index: 1087189 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8922. Min Act: -0.0001

Data Index: 210397 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8685. Min Act: -0.0001

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 3.0315. Min Range: -3.0315

Max Act: 3.0315. Min Act: -0.0001

Data Index: 666434 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8544. Min Act: -0.0001

Data Index: 92582 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.9155. Min Act: -0.0001

Data Index: 586831 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.6630. Min Act: -0.0001

Data Index: 514876 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7629. Min Act: -0.0001

Data Index: 933127 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7762. Min Act: -0.0001

Data Index: 42343 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.6619. Min Act: -0.0001

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7807. Min Act: -0.0001

Data Index: 886155 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7593. Min Act: -0.0001

Data Index: 1352711 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.7880. Min Act: -0.0001

Data Index: 1221617 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.8538. Min Act: -0.0001

Data Index: 889558 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5743. Min Act: -0.0001

Data Index: 983923 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5551. Min Act: -0.0001

Data Index: 767321 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5695. Min Act: -0.0001

Data Index: 234411 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.5315. Min Act: -0.0001

Data Index: 754974 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 3.0315. Min Range: -3.0315

Max Act: 2.4134. Min Act: -0.0001

Data Index: 818899 (C4 (Web Text))

Max Activating Token Index: 636