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

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

Neuron 1200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0002

Data Index: 689918 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0002

Data Index: 95586 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0151. Min Act: -0.0002

Data Index: 820401 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0156. Min Act: -0.0002

Data Index: 59674 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1115778 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0002

Data Index: 963411 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1011425 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0144. Min Act: -0.0002

Data Index: 943506 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0002

Data Index: 108976 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0139. Min Act: -0.0002

Data Index: 490193 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0138. Min Act: -0.0002

Data Index: 586180 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1071729 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1636716 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0133. Min Act: -0.0002

Data Index: 99831 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0134. Min Act: -0.0002

Data Index: 764545 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0002

Data Index: 880269 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0119. Min Act: -0.0002

Data Index: 830715 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1030736 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0130. Min Act: -0.0002

Data Index: 423704 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0133. Min Act: -0.0002

Data Index: 99334 (C4 (Web Text))

Max Activating Token Index: 571