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

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

Neuron 3352 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1396438 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1473430 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1532985 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1384094 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1125704 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1527594 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1486224 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1443043 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1459772 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1567136 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1380016 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1366984 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1593497 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1370287 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3028. Min Act: -0.0000

Data Index: 236709 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1490355 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1450877 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1520849 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1605291 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 0.4131. Min Range: -0.4131

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1406285 (Python Code)

Max Activating Token Index: 161