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

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

Neuron 2521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1155220 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0377. Min Act: -0.0003

Data Index: 117531 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0362. Min Act: -0.0003

Data Index: 107694 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1182581 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0338. Min Act: -0.0002

Data Index: 356274 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0328. Min Act: -0.0003

Data Index: 259792 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1638617 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1055198 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0301. Min Act: -0.0003

Data Index: 186838 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1251053 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1591237 (Python Code)

Max Activating Token Index: 612

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0292. Min Act: -0.0002

Data Index: 807043 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0301. Min Act: -0.0003

Data Index: 932556 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0317. Min Act: -0.0002

Data Index: 188279 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0294. Min Act: -0.0002

Data Index: 678909 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1616248 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1530203 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1464276 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0284. Min Act: -0.0002

Data Index: 197959 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0293. Min Act: -0.0003

Data Index: 13887 (C4 (Web Text))

Max Activating Token Index: 405