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

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

Neuron 1983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.6148. Min Act: -0.0000

Data Index: 1219151 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1300927 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.2554. Min Act: -0.0000

Data Index: 1112651 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.2473. Min Act: -0.0000

Data Index: 412099 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.1673. Min Act: -0.0000

Data Index: 1087971 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.1416. Min Act: -0.0000

Data Index: 915163 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.1378. Min Act: -0.0000

Data Index: 129991 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.1123. Min Act: -0.0000

Data Index: 991028 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9364. Min Act: -0.0000

Data Index: 99342 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.0158. Min Act: -0.0000

Data Index: 42705 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.8787. Min Act: -0.0000

Data Index: 651598 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1492813 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1039497 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1198942 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9579. Min Act: -0.0000

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1291760 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.6148. Min Range: -2.6148

Max Act: 2.0437. Min Act: -0.0000

Data Index: 458738 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9316. Min Act: -0.0000

Data Index: 447749 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1609167 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 2.6148. Min Range: -2.6148

Max Act: 1.9097. Min Act: -0.0000

Data Index: 577394 (C4 (Web Text))

Max Activating Token Index: 11