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

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

Neuron 1920 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1070724 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1069477 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5365. Min Act: -0.0000

Data Index: 164227 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5521. Min Act: -0.0000

Data Index: 135101 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1396961 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5149. Min Act: -0.0000

Data Index: 412461 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5495. Min Act: -0.0000

Data Index: 677907 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5489. Min Act: -0.0000

Data Index: 60199 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1074654 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1418601 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5236. Min Act: -0.0000

Data Index: 808370 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1060492 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5378. Min Act: -0.0000

Data Index: 925340 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1173993 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1475602 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1367463 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5077. Min Act: -0.0000

Data Index: 87499 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.5040. Min Act: -0.0000

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.6275. Min Range: -0.6275

Max Act: 0.4683. Min Act: -0.0000

Data Index: 694921 (C4 (Web Text))

Max Activating Token Index: 718