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

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

Neuron 784 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0194. Min Act: -0.0003

Data Index: 409730 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0171. Min Act: -0.0003

Data Index: 16149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0002

Data Index: 978137 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0156. Min Act: -0.0002

Data Index: 161601 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0200. Min Act: -0.0003

Data Index: 871849 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0119. Min Act: -0.0003

Data Index: 636094 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0175. Min Act: -0.0003

Data Index: 191401 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0133. Min Act: -0.0003

Data Index: 367965 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0154. Min Act: -0.0003

Data Index: 987401 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0141. Min Act: -0.0003

Data Index: 242786 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1378877 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0168. Min Act: -0.0003

Data Index: 68821 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0159. Min Act: -0.0003

Data Index: 579813 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1018569 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0193. Min Act: -0.0003

Data Index: 494368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0136. Min Act: -0.0003

Data Index: 222436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1263534 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0111. Min Act: -0.0003

Data Index: 782460 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0142. Min Act: -0.0003

Data Index: 829679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1426388 (Python Code)

Max Activating Token Index: 22