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

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

Neuron 1968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3178. Min Act: -0.0002

Data Index: 1277002 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3400. Min Act: -0.0002

Data Index: 791719 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3377. Min Act: -0.0002

Data Index: 876944 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3488. Min Act: -0.0002

Data Index: 632188 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3568. Min Act: -0.0002

Data Index: 80149 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3447. Min Act: -0.0002

Data Index: 1114143 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3395. Min Act: -0.0002

Data Index: 991116 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3497. Min Act: -0.0002

Data Index: 177298 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3039. Min Act: -0.0002

Data Index: 43931 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3198. Min Act: -0.0002

Data Index: 637796 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3328. Min Act: -0.0002

Data Index: 1325275 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3319. Min Act: -0.0002

Data Index: 860518 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3214. Min Act: -0.0002

Data Index: 173105 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3052. Min Act: -0.0002

Data Index: 1145522 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3043. Min Act: -0.0002

Data Index: 57381 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3232. Min Act: -0.0002

Data Index: 644120 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3131. Min Act: -0.0002

Data Index: 441488 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2877. Min Act: -0.0002

Data Index: 1277066 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2984. Min Act: -0.0002

Data Index: 966079 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2976. Min Act: -0.0002

Data Index: 656406 (C4 (Web Text))

Max Activating Token Index: 384