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

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

Neuron 4805 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: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1449004 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0359. Min Act: -0.0003

Data Index: 554156 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1216326 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0354. Min Act: -0.0003

Data Index: 759783 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0343. Min Act: -0.0003

Data Index: 45087 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0358. Min Act: -0.0003

Data Index: 627813 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0345. Min Act: -0.0003

Data Index: 273443 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0346. Min Act: -0.0003

Data Index: 530625 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1562776 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0332. Min Act: -0.0003

Data Index: 583116 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0334. Min Act: -0.0003

Data Index: 577983 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0321. Min Act: -0.0003

Data Index: 79378 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1019525 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1303545 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1362079 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0322. Min Act: -0.0003

Data Index: 835386 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0314. Min Act: -0.0003

Data Index: 789020 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1396248 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0318. Min Act: -0.0003

Data Index: 952564 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1152913 (C4 (Web Text))

Max Activating Token Index: 102