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

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

Neuron 3403 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: 0.9278. Min Range: -0.9278

Max Act: 0.8944. Min Act: -0.0000

Data Index: 457413 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1366133 (Python Code)

Max Activating Token Index: 479

Text #2

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1468086 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1499383 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8972. Min Act: -0.0000

Data Index: 500691 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1375434 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8277. Min Act: -0.0000

Data Index: 328923 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1616201 (Python Code)

Max Activating Token Index: 591

Text #8

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1510764 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1579561 (Python Code)

Max Activating Token Index: 354

Text #10

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8576. Min Act: -0.0000

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1158382 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1480611 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1602014 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7582. Min Act: -0.0000

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1641081 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1546929 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8194. Min Act: -0.0000

Data Index: 555794 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7929. Min Act: -0.0000

Data Index: 197314 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1407388 (Python Code)

Max Activating Token Index: 930