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

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

Neuron 2485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.9541. Min Act: -0.0000

Data Index: 626900 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.9232. Min Act: 0.0001

Data Index: 680771 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 1.0180. Min Range: -1.0180

Max Act: 1.0180. Min Act: -0.0000

Data Index: 792301 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.8466. Min Act: -0.0000

Data Index: 273866 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7997. Min Act: 0.0000

Data Index: 1270476 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1151381 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7368. Min Act: -0.0000

Data Index: 108682 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1046980 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.8654. Min Act: -0.0000

Data Index: 234515 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1078654 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7805. Min Act: 0.0000

Data Index: 1001033 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7184. Min Act: -0.0000

Data Index: 713279 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6182. Min Act: -0.0000

Data Index: 422375 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.7054. Min Act: -0.0000

Data Index: 145673 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1313913 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6745. Min Act: -0.0000

Data Index: 163311 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6682. Min Act: 0.0000

Data Index: 245640 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6476. Min Act: -0.0000

Data Index: 792791 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1176088 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.0180. Min Range: -1.0180

Max Act: 0.6393. Min Act: 0.0000

Data Index: 639711 (C4 (Web Text))

Max Activating Token Index: 228