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

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

Neuron 5487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.3055. Min Act: -0.0001

Data Index: 291073 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.1862. Min Act: -0.0001

Data Index: 585445 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.1064. Min Act: -0.0001

Data Index: 1049167 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0042. Min Act: -0.0001

Data Index: 452466 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9791. Min Act: -0.0001

Data Index: 914287 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0767. Min Act: -0.0001

Data Index: 702304 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0227. Min Act: -0.0001

Data Index: 160836 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0457. Min Act: -0.0001

Data Index: 465679 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0263. Min Act: -0.0001

Data Index: 449956 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9915. Min Act: -0.0001

Data Index: 742477 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.3055. Min Range: -1.3055

Max Act: 1.0312. Min Act: -0.0001

Data Index: 376325 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1352287 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9744. Min Act: -0.0001

Data Index: 575964 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9388. Min Act: -0.0001

Data Index: 608327 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1480454 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9208. Min Act: -0.0001

Data Index: 81779 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1168514 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9720. Min Act: -0.0001

Data Index: 289695 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1531231 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9468. Min Act: -0.0001

Data Index: 517757 (C4 (Web Text))

Max Activating Token Index: 734