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

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

Neuron 3905 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: 1.6868. Min Range: -1.6868

Max Act: 1.6868. Min Act: -0.0001

Data Index: 120412 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.5244. Min Act: -0.0001

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4698. Min Act: -0.0001

Data Index: 546930 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4327. Min Act: -0.0001

Data Index: 712421 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4469. Min Act: -0.0001

Data Index: 429978 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.3163. Min Act: -0.0001

Data Index: 627585 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.3290. Min Act: -0.0001

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2094. Min Act: -0.0001

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.1527. Min Act: -0.0001

Data Index: 822165 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0574. Min Act: -0.0001

Data Index: 86701 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0714. Min Act: -0.0001

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.1295. Min Act: -0.0001

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0967. Min Act: -0.0001

Data Index: 893322 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1304828 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.6868. Min Range: -1.6868

Max Act: 0.9765. Min Act: -0.0001

Data Index: 326078 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0490. Min Act: -0.0001

Data Index: 737121 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.0158. Min Act: -0.0001

Data Index: 338649 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.6868. Min Range: -1.6868

Max Act: 0.9474. Min Act: -0.0001

Data Index: 58157 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.6868. Min Range: -1.6868

Max Act: 0.9579. Min Act: -0.0001

Data Index: 358134 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.6868. Min Range: -1.6868

Max Act: 0.9715. Min Act: -0.0001

Data Index: 676048 (C4 (Web Text))

Max Activating Token Index: 907