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

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

Neuron 3101 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4809. Min Act: -0.0002

Data Index: 1248354 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3951. Min Act: -0.0002

Data Index: 1320490 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4372. Min Act: -0.0002

Data Index: 249719 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4015. Min Act: -0.0002

Data Index: 1281329 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3625. Min Act: -0.0002

Data Index: 622899 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3752. Min Act: -0.0002

Data Index: 62754 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3759. Min Act: -0.0002

Data Index: 127916 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3513. Min Act: -0.0002

Data Index: 1264622 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3598. Min Act: -0.0002

Data Index: 556475 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3153. Min Act: -0.0002

Data Index: 70293 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3357. Min Act: -0.0002

Data Index: 1280789 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3309. Min Act: -0.0002

Data Index: 254058 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3056. Min Act: -0.0002

Data Index: 987348 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3497. Min Act: -0.0002

Data Index: 3421 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3716. Min Act: -0.0002

Data Index: 670426 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.2992. Min Act: -0.0002

Data Index: 369541 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3186. Min Act: -0.0003

Data Index: 837761 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3052. Min Act: -0.0002

Data Index: 70465 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3086. Min Act: -0.0002

Data Index: 124977 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3062. Min Act: -0.0002

Data Index: 1048812 (C4 (Web Text))

Max Activating Token Index: 309