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

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

Neuron 2252 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.9499. Min Act: -0.0000

Data Index: 566605 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.9063. Min Act: -0.0000

Data Index: 423403 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 2.0027. Min Range: -2.0027

Max Act: 2.0027. Min Act: -0.0000

Data Index: 590204 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.8809. Min Act: -0.0000

Data Index: 854560 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1304183 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.9192. Min Act: -0.0000

Data Index: 751393 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.7823. Min Act: -0.0000

Data Index: 1342050 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.7482. Min Act: -0.0000

Data Index: 1197343 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.7473. Min Act: -0.0000

Data Index: 26736 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.7229. Min Act: -0.0000

Data Index: 982764 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.7206. Min Act: -0.0000

Data Index: 1182675 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.6047. Min Act: -0.0000

Data Index: 968085 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.5414. Min Act: -0.0000

Data Index: 893645 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1210004 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.6045. Min Act: -0.0000

Data Index: 559921 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.5915. Min Act: -0.0000

Data Index: 139787 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.6770. Min Act: 0.0000

Data Index: 31880 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.6803. Min Act: -0.0000

Data Index: 1228753 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1099545 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 2.0027. Min Range: -2.0027

Max Act: 1.5740. Min Act: -0.0000

Data Index: 104925 (C4 (Web Text))

Max Activating Token Index: 988