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

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

Neuron 4418 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1227094 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1000. Min Act: -0.0002

Data Index: 196985 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1154450 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1280135 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0877. Min Act: -0.0002

Data Index: 716656 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0896. Min Act: -0.0002

Data Index: 635125 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0812. Min Act: -0.0002

Data Index: 594752 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0772. Min Act: -0.0002

Data Index: 957801 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1094506 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1178098 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0761. Min Act: -0.0002

Data Index: 183171 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1098509 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1078738 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1345160 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0774. Min Act: -0.0002

Data Index: 177965 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0706. Min Act: -0.0002

Data Index: 183144 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0733. Min Act: -0.0002

Data Index: 372436 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1292056 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1260644 (C4 (Web Text))

Max Activating Token Index: 36