Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1210 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0207. Min Range: -1.0207

Max Act: 1.0207. Min Act: -0.0000

Data Index: 741989 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.9582. Min Act: -0.0000

Data Index: 737220 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.8132. Min Act: -0.0000

Data Index: 414543 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1221562 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7967. Min Act: -0.0000

Data Index: 585051 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1358227 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7678. Min Act: -0.0000

Data Index: 179193 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7871. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7925. Min Act: -0.0000

Data Index: 652567 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1221383 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1241011 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7855. Min Act: -0.0000

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.8078. Min Act: -0.0000

Data Index: 496829 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1117569 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7476. Min Act: -0.0000

Data Index: 577213 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.6868. Min Act: -0.0000

Data Index: 21104 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1012112 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1048067 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1288872 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.6820. Min Act: -0.0000

Data Index: 63362 (C4 (Web Text))

Max Activating Token Index: 244