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

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

Neuron 3484 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6582. Min Act: -0.0001

Data Index: 721836 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: -0.0001

Data Index: 487340 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6396. Min Act: -0.0001

Data Index: 183968 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5991. Min Act: -0.0001

Data Index: 405150 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5912. Min Act: -0.0001

Data Index: 547281 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1247800 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5839. Min Act: -0.0001

Data Index: 305352 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5336. Min Act: -0.0001

Data Index: 171443 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5411. Min Act: -0.0001

Data Index: 394606 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5414. Min Act: -0.0001

Data Index: 999339 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1357046 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5754. Min Act: -0.0001

Data Index: 689228 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5577. Min Act: -0.0001

Data Index: 568247 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5402. Min Act: -0.0001

Data Index: 747544 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1262135 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5466. Min Act: -0.0001

Data Index: 879625 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5232. Min Act: -0.0001

Data Index: 959007 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1146336 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5190. Min Act: -0.0001

Data Index: 590312 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5064. Min Act: -0.0001

Data Index: 396688 (C4 (Web Text))

Max Activating Token Index: 433