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

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

Neuron 4445 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: 0.0419. Min Range: -0.0419

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1033061 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1183389 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0002

Data Index: 717568 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0403. Min Act: -0.0002

Data Index: 561162 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0350. Min Act: -0.0002

Data Index: 17543 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0364. Min Act: -0.0002

Data Index: 541497 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0378. Min Act: -0.0002

Data Index: 677280 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0338. Min Act: -0.0002

Data Index: 171299 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1518308 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1012389 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0363. Min Act: -0.0002

Data Index: 201888 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0366. Min Act: -0.0002

Data Index: 390128 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0253. Min Act: -0.0002

Data Index: 594558 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1419730 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1537187 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0370. Min Act: -0.0002

Data Index: 220067 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1617511 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0332. Min Act: -0.0002

Data Index: 261526 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0314. Min Act: -0.0002

Data Index: 344112 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1280112 (C4 (Web Text))

Max Activating Token Index: 855