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

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

Neuron 5030 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.1048. Min Act: -0.0000

Data Index: 492368 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.7329. Min Act: -0.0000

Data Index: 377009 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6605. Min Act: -0.0000

Data Index: 293112 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5436. Min Act: -0.0000

Data Index: 304234 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5868. Min Act: -0.0000

Data Index: 182317 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1327687 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5190. Min Act: -0.0000

Data Index: 694828 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1062776 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5449. Min Act: -0.0000

Data Index: 88544 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5351. Min Act: -0.0000

Data Index: 945744 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1280086 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4813. Min Act: -0.0000

Data Index: 695764 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4657. Min Act: -0.0000

Data Index: 537457 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5207. Min Act: -0.0000

Data Index: 130362 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.5116. Min Act: -0.0000

Data Index: 537652 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1279809 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4874. Min Act: -0.0000

Data Index: 45960 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4475. Min Act: -0.0000

Data Index: 976135 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4308. Min Act: -0.0000

Data Index: 734861 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.4387. Min Act: -0.0000

Data Index: 146406 (C4 (Web Text))

Max Activating Token Index: 34