Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1546826 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1419075 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1516768 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0431. Min Act: -0.0003

Data Index: 526617 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0003

Data Index: 469482 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1547727 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1114223 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0400. Min Act: -0.0003

Data Index: 482167 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0397. Min Act: -0.0003

Data Index: 297627 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1608718 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1422531 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1625320 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0378. Min Act: -0.0003

Data Index: 526083 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1197357 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1270459 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1387039 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1180017 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0367. Min Act: -0.0003

Data Index: 434075 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0377. Min Act: -0.0003

Data Index: 415909 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1279673 (C4 (Web Text))

Max Activating Token Index: 572