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

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

Neuron 2728 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.9297. Min Act: -0.0001

Data Index: 1005644 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.9301. Min Act: -0.0002

Data Index: 45373 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8867. Min Act: -0.0002

Data Index: 1166091 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.9072. Min Act: -0.0001

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.9179. Min Act: -0.0002

Data Index: 1156118 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8563. Min Act: -0.0002

Data Index: 573757 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8900. Min Act: -0.0001

Data Index: 766810 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7968. Min Act: -0.0001

Data Index: 166092 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8335. Min Act: -0.0002

Data Index: 1190489 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8000. Min Act: -0.0002

Data Index: 772896 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8129. Min Act: -0.0002

Data Index: 358432 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7716. Min Act: -0.0001

Data Index: 1190877 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7456. Min Act: -0.0001

Data Index: 107276 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7737. Min Act: -0.0001

Data Index: 415947 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.8022. Min Act: -0.0001

Data Index: 694208 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.6801. Min Act: -0.0001

Data Index: 651694 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7231. Min Act: -0.0001

Data Index: 815530 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.7993. Min Act: -0.0002

Data Index: 1126228 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.6881. Min Act: -0.0002

Data Index: 1187681 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.9301. Min Range: -0.9301

Max Act: 0.6799. Min Act: -0.0001

Data Index: 400336 (C4 (Web Text))

Max Activating Token Index: 316