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

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

Neuron 3144 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: 0.3751. Min Range: -0.3751

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1650145 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1274073 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1087734 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1423980 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2276. Min Act: -0.0000

Data Index: 232821 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2491. Min Act: -0.0000

Data Index: 168443 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1162547 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1584641 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1642715 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1980. Min Act: -0.0000

Data Index: 18370 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1561429 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1459969 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1602025 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1301155 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1329699 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1567999 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1392493 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1323. Min Act: -0.0000

Data Index: 657125 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1569647 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 0.3751. Min Range: -0.3751

Max Act: 0.1482. Min Act: -0.0000

Data Index: 840623 (C4 (Web Text))

Max Activating Token Index: 575