Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 367 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1350767 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0341. Min Act: -0.0004

Data Index: 1167593 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1073555 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0350. Min Act: -0.0004

Data Index: 1168412 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0378. Min Act: -0.0004

Data Index: 595217 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1206704 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0004

Data Index: 877480 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0375. Min Act: -0.0004

Data Index: 262790 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0381. Min Act: -0.0004

Data Index: 718778 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0004

Data Index: 758288 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0377. Min Act: -0.0004

Data Index: 168236 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0353. Min Act: -0.0004

Data Index: 208552 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1250639 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1139149 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0378. Min Act: -0.0004

Data Index: 449497 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1097767 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1563212 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0340. Min Act: -0.0004

Data Index: 195137 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1290230 (C4 (Web Text))

Max Activating Token Index: 335