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

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

Neuron 3066 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: 0.3389. Min Range: -0.3389

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1127510 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.3389. Min Act: -0.0000

Data Index: 112696 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1294273 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.3037. Min Act: -0.0000

Data Index: 249163 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1297586 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2487. Min Act: -0.0000

Data Index: 540873 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1137137 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2365. Min Act: -0.0000

Data Index: 473856 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1256093 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1013523 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2297. Min Act: -0.0000

Data Index: 621277 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2313. Min Act: -0.0000

Data Index: 349353 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1216976 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2161. Min Act: -0.0000

Data Index: 444694 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1533612 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1163918 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1008659 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2193. Min Act: -0.0000

Data Index: 484661 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1370834 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2115. Min Act: -0.0000

Data Index: 20176 (C4 (Web Text))

Max Activating Token Index: 104