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

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

Neuron 3478 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: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1472718 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1515167 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1416485 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1383245 (Python Code)

Max Activating Token Index: 540

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1514011 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1372448 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1441173 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1384843 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1031997 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1133611 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1205198 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1653856 (Python Code)

Max Activating Token Index: 153

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0140. Min Act: -0.0003

Data Index: 469038 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1650785 (Python Code)

Max Activating Token Index: 840

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1565915 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0134. Min Act: -0.0003

Data Index: 570484 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1588997 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1641449 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1529612 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1467034 (Python Code)

Max Activating Token Index: 446