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

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

Neuron 3240 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: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0338. Min Act: -0.0003

Data Index: 30982 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0334. Min Act: -0.0003

Data Index: 281208 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0332. Min Act: -0.0003

Data Index: 188311 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0301. Min Act: -0.0003

Data Index: 993608 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0292. Min Act: -0.0003

Data Index: 141314 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0290. Min Act: -0.0003

Data Index: 367789 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1048074 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1075114 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0265. Min Act: -0.0003

Data Index: 193641 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0268. Min Act: -0.0003

Data Index: 100227 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0257. Min Act: -0.0003

Data Index: 506550 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0264. Min Act: -0.0003

Data Index: 671294 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0252. Min Act: -0.0003

Data Index: 782199 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0263. Min Act: -0.0003

Data Index: 378223 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0256. Min Act: -0.0003

Data Index: 599911 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0254. Min Act: -0.0003

Data Index: 454271 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0259. Min Act: -0.0003

Data Index: 927605 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0248. Min Act: -0.0003

Data Index: 620082 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0245. Min Act: -0.0003

Data Index: 957775 (C4 (Web Text))

Max Activating Token Index: 742