Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2398 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0003

Data Index: 170081 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0003

Data Index: 567286 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0003

Data Index: 482597 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0003

Data Index: 921962 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0183. Min Act: -0.0003

Data Index: 842715 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1357694 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1246009 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0170. Min Act: -0.0003

Data Index: 92853 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0169. Min Act: -0.0003

Data Index: 96950 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1170571 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1288136 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0166. Min Act: -0.0003

Data Index: 702411 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0166. Min Act: -0.0003

Data Index: 685095 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0165. Min Act: -0.0003

Data Index: 778947 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0162. Min Act: -0.0003

Data Index: 338676 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1345507 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0161. Min Act: -0.0003

Data Index: 922177 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0160. Min Act: -0.0003

Data Index: 489122 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0160. Min Act: -0.0003

Data Index: 170496 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1650129 (Python Code)

Max Activating Token Index: 346