Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3163 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1084234 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1223. Min Act: -0.0000

Data Index: 121067 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1202362 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1287555 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8877. Min Act: -0.0000

Data Index: 667270 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8739. Min Act: -0.0000

Data Index: 86440 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8440. Min Act: -0.0000

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8527. Min Act: -0.0000

Data Index: 611118 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8144. Min Act: -0.0000

Data Index: 273418 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8045. Min Act: -0.0000

Data Index: 513762 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7456. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1150538 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7676. Min Act: -0.0000

Data Index: 612221 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7384. Min Act: -0.0000

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.8422. Min Act: -0.0000

Data Index: 671008 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7244. Min Act: -0.0000

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.6823. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.6870. Min Act: -0.0000

Data Index: 69313 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.2939. Min Range: -1.2939

Max Act: 0.7339. Min Act: -0.0000

Data Index: 6530 (C4 (Web Text))

Max Activating Token Index: 183