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

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

Neuron 2974 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1447536 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1391045 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1446416 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1491874 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1491476 (Python Code)

Max Activating Token Index: 292

Text #5

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1620375 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3910. Min Act: -0.0000

Data Index: 32945 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3106. Min Act: -0.0000

Data Index: 492167 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3108. Min Act: -0.0000

Data Index: 59385 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1354666 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2061. Min Act: -0.0000

Data Index: 957354 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2674. Min Act: -0.0000

Data Index: 432825 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3378. Min Act: -0.0000

Data Index: 1345122 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1473183 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2476. Min Act: -0.0000

Data Index: 676405 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.3148. Min Act: -0.0000

Data Index: 143468 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1617133 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1403241 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1440658 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 1.6542. Min Range: -1.6542

Max Act: 1.1836. Min Act: -0.0000

Data Index: 287642 (C4 (Web Text))

Max Activating Token Index: 496