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

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

Neuron 976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.8877. Min Act: -0.0000

Data Index: 1185564 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.7119. Min Act: -0.0000

Data Index: 392532 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.6216. Min Act: -0.0000

Data Index: 562127 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.5640. Min Act: -0.0000

Data Index: 324257 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.6045. Min Act: -0.0000

Data Index: 732115 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.6165. Min Act: -0.0000

Data Index: 673768 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1088071 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.4871. Min Act: -0.0000

Data Index: 790640 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.5615. Min Act: -0.0000

Data Index: 244956 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.4194. Min Act: -0.0000

Data Index: 925346 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.4207. Min Act: -0.0000

Data Index: 509141 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.4164. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1018183 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1220965 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1103062 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3500. Min Act: -0.0000

Data Index: 294352 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3708. Min Act: -0.0000

Data Index: 201103 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3986. Min Act: -0.0000

Data Index: 232463 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1003927 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.8877. Min Range: -1.8877

Max Act: 1.3378. Min Act: -0.0000

Data Index: 1318103 (C4 (Web Text))

Max Activating Token Index: 607