Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6327. Min Range: -3.6327

Max Act: 3.6327. Min Act: -0.0000

Data Index: 1190436 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 3.6327. Min Range: -3.6327

Max Act: 3.1308. Min Act: -0.0000

Data Index: 631635 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8705. Min Act: -0.0000

Data Index: 455190 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8415. Min Act: -0.0000

Data Index: 1043502 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.9570. Min Act: -0.0000

Data Index: 962952 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8980. Min Act: -0.0000

Data Index: 350995 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.7257. Min Act: -0.0000

Data Index: 612310 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8792. Min Act: -0.0000

Data Index: 936286 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8086. Min Act: -0.0000

Data Index: 1156282 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.6245. Min Act: -0.0000

Data Index: 955061 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.7149. Min Act: -0.0000

Data Index: 126563 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.7137. Min Act: -0.0000

Data Index: 69740 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.6787. Min Act: -0.0000

Data Index: 339558 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.8190. Min Act: -0.0000

Data Index: 261660 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.7038. Min Act: -0.0000

Data Index: 88839 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.5494. Min Act: -0.0000

Data Index: 383179 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.3683. Min Act: -0.0000

Data Index: 23738 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.6231. Min Act: -0.0000

Data Index: 169174 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.4888. Min Act: -0.0000

Data Index: 1329975 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 3.6327. Min Range: -3.6327

Max Act: 2.5015. Min Act: -0.0000

Data Index: 1131484 (C4 (Web Text))

Max Activating Token Index: 151