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

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

Neuron 1645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.4028. Min Act: -0.0000

Data Index: 259967 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1283895 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.2851. Min Act: -0.0000

Data Index: 186815 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1146538 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0788. Min Act: -0.0000

Data Index: 447780 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1116686 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0571. Min Act: -0.0000

Data Index: 510603 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9908. Min Act: -0.0000

Data Index: 12293 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1121306 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0812. Min Act: -0.0000

Data Index: 454864 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9226. Min Act: -0.0000

Data Index: 40157 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9794. Min Act: -0.0000

Data Index: 20281 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.4028. Min Range: -1.4028

Max Act: 1.0212. Min Act: -0.0000

Data Index: 34201 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9534. Min Act: -0.0000

Data Index: 801116 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9345. Min Act: -0.0000

Data Index: 745915 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1278341 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9179. Min Act: -0.0000

Data Index: 980852 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.9519. Min Act: -0.0000

Data Index: 523507 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.8903. Min Act: -0.0000

Data Index: 165262 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.4028. Min Range: -1.4028

Max Act: 0.8816. Min Act: -0.0000

Data Index: 967195 (C4 (Web Text))

Max Activating Token Index: 880