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

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

Neuron 3909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3694. Min Act: -0.0001

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3927. Min Act: -0.0001

Data Index: 376284 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.4334. Min Act: -0.0001

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.4060. Min Act: -0.0001

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.4027. Min Act: -0.0001

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3483. Min Act: -0.0001

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3512. Min Act: -0.0001

Data Index: 542745 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3582. Min Act: -0.0001

Data Index: 494583 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3401. Min Act: -0.0001

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3262. Min Act: -0.0001

Data Index: 940873 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1013608 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1243304 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1031000 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3201. Min Act: -0.0001

Data Index: 30574 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3362. Min Act: -0.0001

Data Index: 333420 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3005. Min Act: -0.0001

Data Index: 714495 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3113. Min Act: -0.0001

Data Index: 993498 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3141. Min Act: -0.0001

Data Index: 824969 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3169. Min Act: -0.0001

Data Index: 941837 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.2992. Min Act: -0.0001

Data Index: 26828 (C4 (Web Text))

Max Activating Token Index: 721