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

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

Neuron 733 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3229. Min Range: -9.3229

Max Act: 9.3229. Min Act: -0.0001

Data Index: 1144128 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 9.3229. Min Range: -9.3229

Max Act: 8.8111. Min Act: -0.0001

Data Index: 762778 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 9.3229. Min Range: -9.3229

Max Act: 8.8551. Min Act: -0.0001

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 9.3229. Min Range: -9.3229

Max Act: 8.1025. Min Act: -0.0001

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.9882. Min Act: -0.0001

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.9294. Min Act: -0.0001

Data Index: 840928 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.7944. Min Act: -0.0002

Data Index: 800561 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.7804. Min Act: -0.0002

Data Index: 813891 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.7291. Min Act: -0.0002

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.7265. Min Act: -0.0002

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.6986. Min Act: -0.0002

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.8121. Min Act: -0.0001

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.6036. Min Act: -0.0001

Data Index: 775341 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.5902. Min Act: -0.0002

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.6901. Min Act: -0.0001

Data Index: 1112932 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.5291. Min Act: -0.0001

Data Index: 693417 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.5037. Min Act: -0.0002

Data Index: 1002560 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.4988. Min Act: -0.0002

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.4542. Min Act: -0.0001

Data Index: 1332371 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 9.3229. Min Range: -9.3229

Max Act: 7.4212. Min Act: -0.0001

Data Index: 365995 (C4 (Web Text))

Max Activating Token Index: 83