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

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

Neuron 2583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1948. Min Range: -2.1948

Max Act: 2.1948. Min Act: -0.0000

Data Index: 674337 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1545023 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.9812. Min Act: -0.0000

Data Index: 168739 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1320131 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1643365 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.4725. Min Act: -0.0000

Data Index: 1237307 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1480337 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.9942. Min Act: -0.0000

Data Index: 1484012 (Python Code)

Max Activating Token Index: 787

Text #8

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.8713. Min Act: -0.0000

Data Index: 898090 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1552027 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.6393. Min Act: -0.0000

Data Index: 915172 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.5436. Min Act: -0.0000

Data Index: 651894 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.7208. Min Act: -0.0000

Data Index: 576341 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1499501 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1381969 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.7359. Min Act: -0.0000

Data Index: 1472215 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.6783. Min Act: -0.0000

Data Index: 759010 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.5568. Min Act: -0.0000

Data Index: 1604528 (Python Code)

Max Activating Token Index: 213

Text #18

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1553707 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 2.1948. Min Range: -2.1948

Max Act: 1.6278. Min Act: -0.0000

Data Index: 145155 (C4 (Web Text))

Max Activating Token Index: 231