Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1443161 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0006

Data Index: 753218 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0005

Data Index: 1508178 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0006

Data Index: 749866 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0180. Min Act: -0.0005

Data Index: 1428319 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0173. Min Act: -0.0005

Data Index: 1410715 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0178. Min Act: -0.0005

Data Index: 595449 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0175. Min Act: -0.0005

Data Index: 1647998 (Python Code)

Max Activating Token Index: 889

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0173. Min Act: -0.0006

Data Index: 588919 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0171. Min Act: -0.0006

Data Index: 402218 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0170. Min Act: -0.0005

Data Index: 927982 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1296520 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1326601 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1307208 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1564330 (Python Code)

Max Activating Token Index: 820

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1208179 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0167. Min Act: -0.0006

Data Index: 201600 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1109555 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0165. Min Act: -0.0006

Data Index: 915744 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0169. Min Act: -0.0007

Data Index: 594333 (C4 (Web Text))

Max Activating Token Index: 110