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

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

Neuron 3281 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: 1.3575. Min Range: -1.3575

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1619777 (Python Code)

Max Activating Token Index: 695

Text #1

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1596578 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1539720 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1640961 (Python Code)

Max Activating Token Index: 750

Text #4

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1640990 (Python Code)

Max Activating Token Index: 903

Text #5

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1556223 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1654203 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1378626 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1576998 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 1.3575. Min Range: -1.3575

Max Act: 1.0035. Min Act: -0.0000

Data Index: 351987 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1485150 (Python Code)

Max Activating Token Index: 917

Text #11

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1613252 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1655199 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8686. Min Act: 0.0000

Data Index: 1432823 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1429901 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1415341 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1642132 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1401051 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.8282. Min Act: 0.0000

Data Index: 1412422 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.3575. Min Range: -1.3575

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1576497 (Python Code)

Max Activating Token Index: 210