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

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

Neuron 2964 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0001

Data Index: 834286 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4861. Min Act: -0.0001

Data Index: 521707 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1331049 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4086. Min Act: -0.0001

Data Index: 829420 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4269. Min Act: -0.0001

Data Index: 213001 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3784. Min Act: -0.0001

Data Index: 690808 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4139. Min Act: -0.0001

Data Index: 921882 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4102. Min Act: -0.0001

Data Index: 794608 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4180. Min Act: -0.0001

Data Index: 304683 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4009. Min Act: -0.0001

Data Index: 37458 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4004. Min Act: -0.0001

Data Index: 825261 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1198545 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4193. Min Act: -0.0001

Data Index: 189796 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3599. Min Act: -0.0001

Data Index: 691348 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3500. Min Act: -0.0001

Data Index: 669907 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1357369 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3606. Min Act: -0.0001

Data Index: 609593 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3516. Min Act: -0.0001

Data Index: 350769 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3374. Min Act: -0.0001

Data Index: 637028 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3614. Min Act: -0.0001

Data Index: 179896 (C4 (Web Text))

Max Activating Token Index: 624