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

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

Neuron 2866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0686. Min Range: -3.0686

Max Act: 3.0686. Min Act: -0.0000

Data Index: 683489 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.0686. Min Range: -3.0686

Max Act: 3.0105. Min Act: -0.0000

Data Index: 711327 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.3380. Min Act: -0.0000

Data Index: 446384 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.1621. Min Act: -0.0000

Data Index: 181522 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1200635 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9547. Min Act: -0.0000

Data Index: 283762 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.0810. Min Act: -0.0000

Data Index: 924414 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.1415. Min Act: -0.0000

Data Index: 421207 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.0600. Min Act: -0.0000

Data Index: 698485 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.1175. Min Act: -0.0000

Data Index: 500645 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9982. Min Act: -0.0000

Data Index: 444899 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.0686. Min Range: -3.0686

Max Act: 2.0002. Min Act: -0.0000

Data Index: 1230304 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9288. Min Act: -0.0000

Data Index: 768130 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9208. Min Act: -0.0000

Data Index: 81461 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1006374 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9663. Min Act: -0.0000

Data Index: 568711 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.8454. Min Act: -0.0000

Data Index: 276008 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.9281. Min Act: -0.0000

Data Index: 530024 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.8160. Min Act: -0.0000

Data Index: 1329652 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.0686. Min Range: -3.0686

Max Act: 1.8339. Min Act: -0.0000

Data Index: 146329 (C4 (Web Text))

Max Activating Token Index: 172