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

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

Neuron 4793 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: 4.4215. Min Range: -4.4215

Max Act: 4.2953. Min Act: -0.0000

Data Index: 1636255 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.4215. Min Act: -0.0000

Data Index: 1651343 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.0399. Min Act: -0.0000

Data Index: 1539485 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.0264. Min Act: -0.0000

Data Index: 1629793 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.7846. Min Act: -0.0000

Data Index: 1581948 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.7374. Min Act: -0.0000

Data Index: 1418548 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.7358. Min Act: -0.0000

Data Index: 1538877 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.4140. Min Act: -0.0000

Data Index: 1414182 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.5464. Min Act: -0.0000

Data Index: 1443773 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.4823. Min Act: -0.0000

Data Index: 1489524 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.4057. Min Act: -0.0000

Data Index: 1397683 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.4918. Min Act: -0.0000

Data Index: 1416207 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.2887. Min Act: -0.0000

Data Index: 1547967 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.4226. Min Act: -0.0000

Data Index: 1362099 (Python Code)

Max Activating Token Index: 706

Text #14

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.1139. Min Act: -0.0000

Data Index: 1389465 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.2178. Min Act: -0.0000

Data Index: 1565830 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.3821. Min Act: -0.0000

Data Index: 1645382 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 4.4215. Min Range: -4.4215

Max Act: 2.9901. Min Act: -0.0000

Data Index: 1651788 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.0795. Min Act: -0.0000

Data Index: 1545300 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.1953. Min Act: -0.0000

Data Index: 1416460 (Python Code)

Max Activating Token Index: 544