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

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

Neuron 2020 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0001

Data Index: 795444 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0001

Data Index: 842584 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0001

Data Index: 504573 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0142. Min Act: -0.0001

Data Index: 440678 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0157. Min Act: -0.0001

Data Index: 48925 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0001

Data Index: 548301 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0150. Min Act: -0.0001

Data Index: 264656 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0001

Data Index: 178508 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1129858 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1405208 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1121464 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1053619 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0134. Min Act: -0.0001

Data Index: 159533 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1016204 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0127. Min Act: -0.0001

Data Index: 485298 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0146. Min Act: -0.0001

Data Index: 197474 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1208576 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0134. Min Act: -0.0001

Data Index: 832839 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0135. Min Act: -0.0001

Data Index: 705958 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1016287 (C4 (Web Text))

Max Activating Token Index: 11