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

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

Neuron 5492 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1054601 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1105000 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.1232. Min Act: -0.0000

Data Index: 13212 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1078232 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0891. Min Act: -0.0000

Data Index: 679876 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.3291. Min Range: -1.3291

Max Act: 1.0160. Min Act: -0.0000

Data Index: 51404 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1014475 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9252. Min Act: 0.0000

Data Index: 426554 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9858. Min Act: -0.0000

Data Index: 473534 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1129637 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9657. Min Act: -0.0000

Data Index: 446833 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9557. Min Act: -0.0000

Data Index: 29214 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9505. Min Act: -0.0000

Data Index: 364161 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1103585 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1216321 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.8759. Min Act: -0.0000

Data Index: 952739 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9363. Min Act: -0.0000

Data Index: 649299 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1129791 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1155814 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.3291. Min Range: -1.3291

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1322852 (C4 (Web Text))

Max Activating Token Index: 779