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

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

Neuron 3854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1656151 (Python Code)

Max Activating Token Index: 349

Text #1

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1560375 (Python Code)

Max Activating Token Index: 355

Text #2

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.3235. Min Act: -0.0000

Data Index: 191496 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1581535 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1576769 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1453745 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1380777 (Python Code)

Max Activating Token Index: 798

Text #7

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1551663 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1391227 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1465446 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2584. Min Act: -0.0000

Data Index: 802307 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1656495 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1410789 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1626207 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2541. Min Act: -0.0000

Data Index: 298401 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1600329 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1405372 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1523440 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1527232 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 0.4255. Min Range: -0.4255

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1512949 (Python Code)

Max Activating Token Index: 43