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

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

Neuron 1407 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: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0003

Data Index: 270951 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1074369 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1311318 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0335. Min Act: -0.0003

Data Index: 489887 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1169933 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0334. Min Act: -0.0003

Data Index: 751764 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0330. Min Act: -0.0003

Data Index: 771774 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0338. Min Act: -0.0003

Data Index: 59239 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0323. Min Act: -0.0004

Data Index: 516892 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0308. Min Act: -0.0003

Data Index: 965381 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1346723 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0315. Min Act: -0.0003

Data Index: 46466 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0323. Min Act: -0.0003

Data Index: 400326 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0315. Min Act: -0.0003

Data Index: 652295 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0321. Min Act: -0.0003

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0317. Min Act: -0.0003

Data Index: 265392 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1145225 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0293. Min Act: -0.0003

Data Index: 681538 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1031191 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1073655 (C4 (Web Text))

Max Activating Token Index: 581