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

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

Neuron 696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.9877. Min Act: -0.0000

Data Index: 828747 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8116. Min Act: -0.0001

Data Index: 151929 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1092070 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7979. Min Act: -0.0001

Data Index: 642890 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1227641 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1050281 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1314134 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7643. Min Act: -0.0001

Data Index: 95769 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6989. Min Act: -0.0000

Data Index: 236723 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6969. Min Act: -0.0000

Data Index: 624593 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1210274 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7052. Min Act: -0.0000

Data Index: 18199 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1186800 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1165544 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6275. Min Act: -0.0000

Data Index: 424662 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6275. Min Act: -0.0000

Data Index: 976263 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6146. Min Act: -0.0000

Data Index: 980365 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6197. Min Act: -0.0000

Data Index: 383507 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1037481 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6147. Min Act: -0.0001

Data Index: 729317 (C4 (Web Text))

Max Activating Token Index: 603