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

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

Neuron 1603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0149. Min Range: -3.0149

Max Act: 3.0149. Min Act: -0.0000

Data Index: 594334 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.7327. Min Act: -0.0001

Data Index: 709784 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.7135. Min Act: -0.0000

Data Index: 287441 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.6919. Min Act: -0.0000

Data Index: 190488 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.6819. Min Act: -0.0000

Data Index: 1069524 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.5783. Min Act: -0.0000

Data Index: 1186548 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.4059. Min Act: -0.0000

Data Index: 153971 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.6332. Min Act: -0.0000

Data Index: 309076 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.5031. Min Act: -0.0000

Data Index: 1224576 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.4883. Min Act: -0.0000

Data Index: 806963 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3372. Min Act: -0.0000

Data Index: 1019591 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3308. Min Act: -0.0000

Data Index: 725150 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3079. Min Act: -0.0000

Data Index: 563498 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.6952. Min Act: -0.0001

Data Index: 36554 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3255. Min Act: -0.0001

Data Index: 118883 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1115266 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3549. Min Act: -0.0000

Data Index: 972175 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3430. Min Act: -0.0000

Data Index: 63156 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.3341. Min Act: -0.0000

Data Index: 559449 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.0149. Min Range: -3.0149

Max Act: 2.5673. Min Act: -0.0000

Data Index: 1159228 (C4 (Web Text))

Max Activating Token Index: 799