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

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

Neuron 296 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 517355 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1390920 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0156. Min Act: -0.0002

Data Index: 136425 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1406034 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1545414 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0151. Min Act: -0.0002

Data Index: 872220 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0002

Data Index: 794886 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0002

Data Index: 316417 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0002

Data Index: 697727 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1062221 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1615765 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1415926 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0142. Min Act: -0.0002

Data Index: 595050 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1468873 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1303187 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1523405 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0002

Data Index: 619817 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0002

Data Index: 379066 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0002

Data Index: 156883 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1144911 (C4 (Web Text))

Max Activating Token Index: 907