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

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

Neuron 3130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.4868. Min Act: 0.0000

Data Index: 892995 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.2592. Min Act: -0.0000

Data Index: 1116142 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.0112. Min Act: -0.0000

Data Index: 1257707 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.1374. Min Act: -0.0000

Data Index: 1059044 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1253304 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.8287. Min Act: 0.0000

Data Index: 973099 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.8453. Min Act: -0.0000

Data Index: 1147177 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1248445 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.7427. Min Act: -0.0000

Data Index: 581063 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.7275. Min Act: -0.0000

Data Index: 1280098 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.5203. Min Act: -0.0000

Data Index: 880788 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3143. Min Act: -0.0000

Data Index: 732956 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.2779. Min Act: 0.0000

Data Index: 157824 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3710. Min Act: -0.0000

Data Index: 225929 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3684. Min Act: -0.0000

Data Index: 1122675 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3735. Min Act: -0.0000

Data Index: 92687 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1238913 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3282. Min Act: -0.0000

Data Index: 13647 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.1897. Min Act: 0.0001

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1200099 (C4 (Web Text))

Max Activating Token Index: 182