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

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

Neuron 4253 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.7127. Min Act: -0.0000

Data Index: 852025 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5806. Min Act: -0.0000

Data Index: 313628 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1210808 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1208620 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5568. Min Act: -0.0000

Data Index: 115906 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4721. Min Act: -0.0000

Data Index: 730765 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4816. Min Act: -0.0000

Data Index: 433300 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4536. Min Act: -0.0000

Data Index: 693229 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4578. Min Act: -0.0000

Data Index: 76894 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4446. Min Act: -0.0000

Data Index: 729515 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4777. Min Act: -0.0000

Data Index: 588802 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4525. Min Act: -0.0000

Data Index: 461245 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4508. Min Act: -0.0000

Data Index: 273294 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4193. Min Act: -0.0000

Data Index: 899812 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4459. Min Act: -0.0000

Data Index: 122756 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4323. Min Act: -0.0000

Data Index: 732844 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4802. Min Act: -0.0000

Data Index: 560103 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.3863. Min Act: -0.0000

Data Index: 650010 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4154. Min Act: -0.0000

Data Index: 11699 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1091100 (C4 (Web Text))

Max Activating Token Index: 898