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

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

Neuron 573 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.9138. Min Act: -0.0002

Data Index: 488611 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.7343. Min Act: -0.0001

Data Index: 374075 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.7715. Min Act: -0.0001

Data Index: 685231 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6778. Min Act: -0.0001

Data Index: 1031692 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6639. Min Act: -0.0001

Data Index: 925664 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6132. Min Act: -0.0002

Data Index: 1251121 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6811. Min Act: -0.0001

Data Index: 746474 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6859. Min Act: -0.0001

Data Index: 1289678 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6378. Min Act: -0.0001

Data Index: 203203 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6304. Min Act: -0.0001

Data Index: 926715 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6243. Min Act: -0.0001

Data Index: 138828 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6014. Min Act: -0.0001

Data Index: 544034 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6006. Min Act: -0.0001

Data Index: 924305 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6128. Min Act: -0.0001

Data Index: 211675 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1324030 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6712. Min Act: -0.0001

Data Index: 306362 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1260633 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.5679. Min Act: -0.0001

Data Index: 466807 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.5655. Min Act: -0.0001

Data Index: 816649 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.9138. Min Range: -0.9138

Max Act: 0.6169. Min Act: -0.0001

Data Index: 189763 (C4 (Web Text))

Max Activating Token Index: 438