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

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

Neuron 2609 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0002

Data Index: 482787 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0002

Data Index: 946784 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0156. Min Act: -0.0002

Data Index: 498713 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1070911 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1071195 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0002

Data Index: 710475 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1007293 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0149. Min Act: -0.0002

Data Index: 262679 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1357683 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0149. Min Act: -0.0002

Data Index: 291150 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0002

Data Index: 787031 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1274704 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0002

Data Index: 168877 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1233959 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0002

Data Index: 268301 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0002

Data Index: 90034 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0002

Data Index: 698501 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0002

Data Index: 260814 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0002

Data Index: 85407 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0002

Data Index: 748241 (C4 (Web Text))

Max Activating Token Index: 696