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

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

Neuron 4186 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0003

Data Index: 379488 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0322. Min Act: -0.0003

Data Index: 371500 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1267647 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1306718 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0288. Min Act: -0.0002

Data Index: 450201 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0268. Min Act: -0.0003

Data Index: 954663 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1047059 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0276. Min Act: -0.0003

Data Index: 573070 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0282. Min Act: -0.0003

Data Index: 481277 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0280. Min Act: -0.0003

Data Index: 284438 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0267. Min Act: -0.0003

Data Index: 534764 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1077495 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0271. Min Act: -0.0003

Data Index: 702308 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0266. Min Act: -0.0003

Data Index: 139992 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0282. Min Act: -0.0003

Data Index: 373009 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1073569 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0003

Data Index: 860815 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0259. Min Act: -0.0002

Data Index: 649723 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0003

Data Index: 344323 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0263. Min Act: -0.0003

Data Index: 978876 (C4 (Web Text))

Max Activating Token Index: 334