Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1000458 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0393. Min Act: -0.0003

Data Index: 262658 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1283170 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0002

Data Index: 680037 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1106127 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0333. Min Act: -0.0003

Data Index: 238455 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0003

Data Index: 708664 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0350. Min Act: -0.0003

Data Index: 898511 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0346. Min Act: -0.0003

Data Index: 313432 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0322. Min Act: -0.0003

Data Index: 113980 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1322319 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0311. Min Act: -0.0003

Data Index: 275907 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0332. Min Act: -0.0003

Data Index: 653799 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0323. Min Act: -0.0003

Data Index: 479214 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1152527 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0315. Min Act: -0.0004

Data Index: 828723 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1153001 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1325686 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0302. Min Act: -0.0003

Data Index: 987851 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0286. Min Act: -0.0003

Data Index: 871287 (C4 (Web Text))

Max Activating Token Index: 972