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

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

Neuron 4358 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: 2.4230. Min Range: -2.4230

Max Act: 2.4230. Min Act: -0.0000

Data Index: 656237 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.1803. Min Act: -0.0000

Data Index: 520930 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.1620. Min Act: -0.0000

Data Index: 810166 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.0962. Min Act: -0.0000

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.0807. Min Act: -0.0000

Data Index: 619441 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.9768. Min Act: -0.0000

Data Index: 120823 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.0375. Min Act: -0.0000

Data Index: 790918 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.1190. Min Act: -0.0000

Data Index: 965244 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.9627. Min Act: -0.0000

Data Index: 211909 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 2.4230. Min Range: -2.4230

Max Act: 2.1579. Min Act: -0.0000

Data Index: 637478 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.8830. Min Act: -0.0000

Data Index: 614336 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1032857 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.8205. Min Act: -0.0000

Data Index: 910326 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.7004. Min Act: -0.0000

Data Index: 646220 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.7904. Min Act: -0.0000

Data Index: 1096411 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.7888. Min Act: -0.0000

Data Index: 529505 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.8833. Min Act: -0.0000

Data Index: 841670 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.6879. Min Act: -0.0000

Data Index: 193341 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.5632. Min Act: -0.0000

Data Index: 246729 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.4230. Min Range: -2.4230

Max Act: 1.6006. Min Act: -0.0000

Data Index: 887441 (C4 (Web Text))

Max Activating Token Index: 803