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

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

Neuron 5361 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.0972. Min Act: -0.0001

Data Index: 951952 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.2258. Min Act: -0.0001

Data Index: 914972 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8615. Min Act: -0.0001

Data Index: 320678 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1155290 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8826. Min Act: -0.0001

Data Index: 805408 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8488. Min Act: -0.0001

Data Index: 1130905 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8582. Min Act: -0.0001

Data Index: 905204 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7974. Min Act: -0.0001

Data Index: 1092243 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8700. Min Act: -0.0001

Data Index: 761513 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8364. Min Act: -0.0001

Data Index: 388478 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8563. Min Act: -0.0001

Data Index: 752571 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7751. Min Act: -0.0001

Data Index: 652193 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7490. Min Act: -0.0001

Data Index: 10959 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7291. Min Act: -0.0001

Data Index: 316234 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7948. Min Act: -0.0001

Data Index: 114832 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1070576 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7553. Min Act: -0.0001

Data Index: 350523 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7538. Min Act: -0.0001

Data Index: 1292287 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7468. Min Act: -0.0001

Data Index: 917775 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7685. Min Act: -0.0001

Data Index: 514082 (C4 (Web Text))

Max Activating Token Index: 128