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

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

Neuron 3637 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1291710 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1020929 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.8168. Min Act: -0.0001

Data Index: 1325279 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1044879 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7417. Min Act: -0.0000

Data Index: 777750 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1109010 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1277955 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7017. Min Act: -0.0001

Data Index: 472822 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6968. Min Act: -0.0001

Data Index: 895606 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6277. Min Act: -0.0001

Data Index: 1163972 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5764. Min Act: -0.0001

Data Index: 426798 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6598. Min Act: -0.0001

Data Index: 756505 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1020771 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5609. Min Act: -0.0001

Data Index: 588416 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6339. Min Act: -0.0001

Data Index: 1289790 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6172. Min Act: -0.0001

Data Index: 1177518 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5895. Min Act: -0.0000

Data Index: 923300 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6368. Min Act: -0.0001

Data Index: 596426 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6041. Min Act: -0.0000

Data Index: 736485 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1233790 (C4 (Web Text))

Max Activating Token Index: 79