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

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

Neuron 4653 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: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0002

Data Index: 417832 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0377. Min Act: -0.0002

Data Index: 189469 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1097411 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1223323 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0382. Min Act: -0.0002

Data Index: 909964 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0354. Min Act: -0.0002

Data Index: 552863 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1267012 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1218018 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0309. Min Act: -0.0002

Data Index: 485643 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0377. Min Act: -0.0002

Data Index: 464001 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1281537 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0325. Min Act: -0.0002

Data Index: 863973 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0323. Min Act: -0.0002

Data Index: 426483 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0341. Min Act: -0.0002

Data Index: 70249 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0331. Min Act: -0.0002

Data Index: 85351 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0352. Min Act: -0.0002

Data Index: 809223 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1045413 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1184051 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0307. Min Act: -0.0002

Data Index: 733524 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0285. Min Act: -0.0002

Data Index: 464191 (C4 (Web Text))

Max Activating Token Index: 53