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

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

Neuron 95 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: 0.0464. Min Range: -0.0464

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1175808 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0002

Data Index: 611051 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1305299 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1149420 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0369. Min Act: -0.0002

Data Index: 602425 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1153711 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0367. Min Act: -0.0002

Data Index: 309102 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0358. Min Act: -0.0002

Data Index: 617239 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0362. Min Act: -0.0002

Data Index: 34443 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1260702 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0354. Min Act: -0.0002

Data Index: 945292 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1295535 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0347. Min Act: -0.0002

Data Index: 466935 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0349. Min Act: -0.0002

Data Index: 763625 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0355. Min Act: -0.0002

Data Index: 8014 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0346. Min Act: -0.0002

Data Index: 460484 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0347. Min Act: -0.0002

Data Index: 946192 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0337. Min Act: -0.0002

Data Index: 686373 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0343. Min Act: -0.0002

Data Index: 188824 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0335. Min Act: -0.0002

Data Index: 236280 (C4 (Web Text))

Max Activating Token Index: 455