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

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

Neuron 1337 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: 1.8560. Min Range: -1.8560

Max Act: 1.8560. Min Act: -0.0001

Data Index: 1184994 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1763. Min Act: -0.0001

Data Index: 479677 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.6296. Min Act: -0.0001

Data Index: 865146 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.5225. Min Act: -0.0001

Data Index: 415985 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.4522. Min Act: -0.0001

Data Index: 44190 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.4037. Min Act: -0.0001

Data Index: 472940 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.0377. Min Act: -0.0001

Data Index: 1255383 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2223. Min Act: -0.0001

Data Index: 928552 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.8560. Min Range: -1.8560

Max Act: 0.9774. Min Act: -0.0001

Data Index: 527088 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2312. Min Act: -0.0001

Data Index: 313662 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1072. Min Act: -0.0001

Data Index: 817113 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1774. Min Act: -0.0001

Data Index: 661712 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1240. Min Act: -0.0001

Data Index: 1048972 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1120125 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1549. Min Act: -0.0001

Data Index: 328659 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.0028. Min Act: -0.0001

Data Index: 801644 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1244. Min Act: -0.0001

Data Index: 777793 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.0265. Min Act: -0.0001

Data Index: 672980 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.0429. Min Act: -0.0001

Data Index: 451482 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1283. Min Act: -0.0001

Data Index: 803889 (C4 (Web Text))

Max Activating Token Index: 178