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

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

Neuron 3472 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0002

Data Index: 27878 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0458. Min Act: -0.0002

Data Index: 382088 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0449. Min Act: -0.0002

Data Index: 270925 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0440. Min Act: -0.0002

Data Index: 96587 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0411. Min Act: -0.0002

Data Index: 538803 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1038844 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0411. Min Act: -0.0002

Data Index: 112272 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0396. Min Act: -0.0002

Data Index: 914682 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0414. Min Act: -0.0002

Data Index: 190169 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1094918 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0394. Min Act: -0.0002

Data Index: 393386 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1051421 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0388. Min Act: -0.0002

Data Index: 767986 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1124525 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1226762 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0379. Min Act: -0.0002

Data Index: 904399 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1280978 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0358. Min Act: -0.0002

Data Index: 674470 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1274856 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1215018 (C4 (Web Text))

Max Activating Token Index: 431