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

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

Neuron 4796 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1555445 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3423. Min Act: 0.0000

Data Index: 1547145 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1450562 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1383126 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.1308. Min Act: -0.0000

Data Index: 810337 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1599931 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1402483 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1487905 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1494012 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1620294 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1513311 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1609206 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1378538 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1478143 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1559912 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9726. Min Act: 0.0000

Data Index: 1472424 (Python Code)

Max Activating Token Index: 881

Text #16

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1552593 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1480336 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1503468 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 1.8592. Min Range: -1.8592

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1561663 (Python Code)

Max Activating Token Index: 365