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

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

Neuron 248 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: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1303093 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0348. Min Act: -0.0003

Data Index: 275452 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0348. Min Act: -0.0002

Data Index: 499791 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0331. Min Act: -0.0001

Data Index: 727617 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0340. Min Act: -0.0003

Data Index: 886438 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1335900 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0332. Min Act: -0.0002

Data Index: 892386 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0326. Min Act: -0.0003

Data Index: 488539 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0338. Min Act: -0.0001

Data Index: 69425 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1333397 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0335. Min Act: -0.0001

Data Index: 667236 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1128327 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0326. Min Act: -0.0000

Data Index: 966217 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0321. Min Act: -0.0002

Data Index: 232877 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0324. Min Act: -0.0002

Data Index: 780006 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0318. Min Act: -0.0003

Data Index: 715309 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0320. Min Act: -0.0004

Data Index: 147349 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0312. Min Act: -0.0002

Data Index: 532154 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0323. Min Act: -0.0002

Data Index: 168836 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0310. Min Act: -0.0002

Data Index: 499186 (C4 (Web Text))

Max Activating Token Index: 531