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

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

Neuron 5845 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: 0.4151. Min Range: -0.4151

Max Act: 0.3950. Min Act: -0.0000

Data Index: 86897 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1592363 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1640526 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1457821 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1392089 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1497776 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1484153 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1467931 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1618576 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1386989 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1565155 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1465488 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1647892 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3199. Min Act: -0.0000

Data Index: 807006 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1594348 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1429415 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1572938 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1484396 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1562939 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1527984 (Python Code)

Max Activating Token Index: 53