Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0000

Data Index: 865067 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1166872 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1048092 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0988. Min Act: -0.0000

Data Index: 678626 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1291837 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0931. Min Act: -0.0000

Data Index: 484012 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0926. Min Act: -0.0000

Data Index: 700621 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0924. Min Act: -0.0000

Data Index: 419483 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0878. Min Act: -0.0001

Data Index: 228796 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0901. Min Act: -0.0000

Data Index: 729226 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0867. Min Act: -0.0000

Data Index: 723840 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0850. Min Act: -0.0000

Data Index: 576066 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0854. Min Act: -0.0001

Data Index: 290561 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1052724 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0872. Min Act: -0.0000

Data Index: 782507 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0872. Min Act: -0.0000

Data Index: 892413 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1168524 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1027660 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0919. Min Act: -0.0001

Data Index: 881889 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0819. Min Act: -0.0001

Data Index: 164289 (C4 (Web Text))

Max Activating Token Index: 899