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

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

Neuron 896 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: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0003

Data Index: 50373 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0286. Min Act: -0.0003

Data Index: 614685 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1263168 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0269. Min Act: -0.0002

Data Index: 330228 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0259. Min Act: -0.0002

Data Index: 394892 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0256. Min Act: -0.0002

Data Index: 967253 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0237. Min Act: -0.0002

Data Index: 9477 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0241. Min Act: -0.0003

Data Index: 728453 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0237. Min Act: -0.0003

Data Index: 623808 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0230. Min Act: -0.0003

Data Index: 24858 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0219. Min Act: -0.0003

Data Index: 687881 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1249365 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0218. Min Act: -0.0002

Data Index: 576459 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1080725 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0218. Min Act: -0.0002

Data Index: 430543 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0222. Min Act: -0.0003

Data Index: 17904 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1016955 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1297194 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0216. Min Act: -0.0002

Data Index: 619777 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1348160 (C4 (Web Text))

Max Activating Token Index: 850