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

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

Neuron 3292 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: 2.0384. Min Range: -2.0384

Max Act: 2.0384. Min Act: -0.0000

Data Index: 785224 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1183093 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1320054 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1118943 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3523. Min Act: -0.0000

Data Index: 523469 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.2121. Min Act: -0.0000

Data Index: 706553 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.2911. Min Act: -0.0000

Data Index: 450466 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.2125. Min Act: -0.0000

Data Index: 438737 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3300. Min Act: -0.0000

Data Index: 584975 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3899. Min Act: -0.0000

Data Index: 455857 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.1900. Min Act: -0.0000

Data Index: 478815 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.1828. Min Act: -0.0000

Data Index: 999152 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1323600 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1470391 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1016183 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1104409 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.2922. Min Act: -0.0000

Data Index: 83363 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.3115. Min Act: -0.0000

Data Index: 166847 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.0384. Min Range: -2.0384

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1459791 (Python Code)

Max Activating Token Index: 36