Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.3336. Min Act: -0.0001

Data Index: 50719 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.1558. Min Act: -0.0001

Data Index: 329217 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.1252. Min Act: -0.0001

Data Index: 441765 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0952. Min Act: -0.0001

Data Index: 479270 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0932. Min Act: -0.0001

Data Index: 355087 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.1121. Min Act: -0.0001

Data Index: 1202455 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0580. Min Act: -0.0001

Data Index: 918688 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0571. Min Act: -0.0001

Data Index: 839719 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0862. Min Act: -0.0001

Data Index: 912830 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1047859 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0522. Min Act: -0.0001

Data Index: 714463 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0291. Min Act: -0.0001

Data Index: 1011047 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0236. Min Act: -0.0001

Data Index: 914226 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.3336. Min Range: -1.3336

Max Act: 0.9906. Min Act: -0.0001

Data Index: 1032563 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0320. Min Act: -0.0001

Data Index: 1271545 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0351. Min Act: -0.0001

Data Index: 54168 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0225. Min Act: -0.0001

Data Index: 626714 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.3336. Min Range: -1.3336

Max Act: 1.0225. Min Act: -0.0001

Data Index: 614263 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.3336. Min Range: -1.3336

Max Act: 0.9503. Min Act: -0.0001

Data Index: 260059 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.3336. Min Range: -1.3336

Max Act: 0.9779. Min Act: -0.0001

Data Index: 267047 (C4 (Web Text))

Max Activating Token Index: 100