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

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

Neuron 1629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.8363. Min Act: -0.0000

Data Index: 560007 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1262259 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.7862. Min Act: -0.0001

Data Index: 73799 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.8274. Min Act: -0.0001

Data Index: 562836 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1216201 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.7165. Min Act: -0.0000

Data Index: 46564 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6846. Min Act: -0.0001

Data Index: 5768 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6782. Min Act: -0.0000

Data Index: 674536 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6622. Min Act: -0.0000

Data Index: 375026 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1329981 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6569. Min Act: -0.0001

Data Index: 55423 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6715. Min Act: -0.0000

Data Index: 44322 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1038246 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6273. Min Act: -0.0000

Data Index: 137217 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1163318 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1131743 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6140. Min Act: -0.0000

Data Index: 699923 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5861. Min Act: -0.0001

Data Index: 1294352 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5902. Min Act: -0.0000

Data Index: 696943 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.6079. Min Act: -0.0000

Data Index: 505984 (C4 (Web Text))

Max Activating Token Index: 791