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

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

Neuron 9 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: 0.0446. Min Range: -0.0446

Max Act: 0.0446. Min Act: -0.0004

Data Index: 912115 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0393. Min Act: -0.0004

Data Index: 354639 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0385. Min Act: -0.0004

Data Index: 241332 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0321. Min Act: -0.0004

Data Index: 915237 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0400. Min Act: -0.0004

Data Index: 361409 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0360. Min Act: -0.0004

Data Index: 51515 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0318. Min Act: -0.0004

Data Index: 938798 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1045568 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0346. Min Act: -0.0004

Data Index: 517775 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0334. Min Act: -0.0004

Data Index: 961262 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0316. Min Act: -0.0004

Data Index: 781715 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0340. Min Act: -0.0004

Data Index: 436346 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0333. Min Act: -0.0004

Data Index: 51923 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1056630 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0301. Min Act: -0.0004

Data Index: 622328 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0321. Min Act: -0.0004

Data Index: 153700 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1077587 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0320. Min Act: -0.0004

Data Index: 551128 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0304. Min Act: -0.0004

Data Index: 1322218 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1101222 (C4 (Web Text))

Max Activating Token Index: 747