Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2108 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7316. Min Act: -0.0003

Data Index: 126250 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7267. Min Act: -0.0003

Data Index: 466744 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7133. Min Act: -0.0003

Data Index: 1087198 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7171. Min Act: -0.0003

Data Index: 13979 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6824. Min Act: -0.0003

Data Index: 535045 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7131. Min Act: -0.0003

Data Index: 215123 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.7118. Min Act: -0.0003

Data Index: 697920 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6843. Min Act: -0.0003

Data Index: 1121807 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6766. Min Act: -0.0003

Data Index: 393485 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6506. Min Act: -0.0003

Data Index: 437125 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6244. Min Act: -0.0003

Data Index: 424902 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6813. Min Act: -0.0003

Data Index: 1083986 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6408. Min Act: -0.0003

Data Index: 143450 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6589. Min Act: -0.0003

Data Index: 916802 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6204. Min Act: -0.0003

Data Index: 1013956 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6972. Min Act: -0.0003

Data Index: 1069860 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6071. Min Act: -0.0003

Data Index: 147169 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6072. Min Act: -0.0003

Data Index: 314748 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6284. Min Act: -0.0003

Data Index: 330390 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.7316. Min Range: -0.7316

Max Act: 0.6253. Min Act: -0.0003

Data Index: 817155 (C4 (Web Text))

Max Activating Token Index: 890