Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.6900. Min Act: -0.0000

Data Index: 756766 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.6105. Min Act: -0.0000

Data Index: 1121402 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.6019. Min Act: -0.0000

Data Index: 206942 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.9375. Min Act: -0.0000

Data Index: 763530 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.5122. Min Act: -0.0000

Data Index: 918867 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.4797. Min Act: -0.0000

Data Index: 1169799 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.2129. Min Act: -0.0000

Data Index: 494918 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.3351. Min Act: -0.0000

Data Index: 1309401 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.1472. Min Act: -0.0000

Data Index: 41313 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.5619. Min Act: -0.0000

Data Index: 1128704 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.4425. Min Act: -0.0000

Data Index: 322855 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.5746. Min Act: -0.0000

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.9375. Min Range: -3.9375

Max Act: 2.9275. Min Act: -0.0000

Data Index: 522858 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.2030. Min Act: -0.0000

Data Index: 169344 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.1827. Min Act: -0.0000

Data Index: 1070017 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.1577. Min Act: -0.0000

Data Index: 54392 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.0114. Min Act: -0.0000

Data Index: 1266913 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.2121. Min Act: -0.0000

Data Index: 492750 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.0723. Min Act: -0.0000

Data Index: 315104 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 3.9375. Min Range: -3.9375

Max Act: 2.8443. Min Act: -0.0000

Data Index: 262787 (C4 (Web Text))

Max Activating Token Index: 845