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

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

Neuron 4850 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: 0.2479. Min Range: -0.2479

Max Act: 0.2479. Min Act: -0.0000

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2248. Min Act: -0.0000

Data Index: 281496 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2323. Min Act: -0.0000

Data Index: 664353 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2289. Min Act: -0.0000

Data Index: 980586 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2437. Min Act: -0.0000

Data Index: 522858 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2198. Min Act: -0.0000

Data Index: 708557 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2198. Min Act: -0.0000

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2254. Min Act: -0.0000

Data Index: 859530 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1907. Min Act: -0.0000

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2024. Min Act: -0.0000

Data Index: 965586 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1002459 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2057. Min Act: -0.0000

Data Index: 425121 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1945. Min Act: -0.0000

Data Index: 212838 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1802. Min Act: -0.0000

Data Index: 388610 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1864. Min Act: -0.0000

Data Index: 113744 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1780. Min Act: -0.0000

Data Index: 620868 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1766. Min Act: -0.0000

Data Index: 313792 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1699. Min Act: -0.0000

Data Index: 365923 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1773. Min Act: -0.0000

Data Index: 870739 (C4 (Web Text))

Max Activating Token Index: 234