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

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

Neuron 1488 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: 2.5508. Min Range: -2.5508

Max Act: 2.5508. Min Act: -0.0000

Data Index: 1586337 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 2.5508. Min Range: -2.5508

Max Act: 2.1982. Min Act: -0.0000

Data Index: 1470619 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 2.5508. Min Range: -2.5508

Max Act: 2.1447. Min Act: -0.0000

Data Index: 1486847 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1640066 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 2.5508. Min Range: -2.5508

Max Act: 2.1036. Min Act: -0.0000

Data Index: 1380121 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1484613 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8573. Min Act: -0.0000

Data Index: 1425007 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.7785. Min Act: -0.0000

Data Index: 291003 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8578. Min Act: -0.0000

Data Index: 296537 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1416610 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.7602. Min Act: -0.0000

Data Index: 502892 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.7609. Min Act: -0.0000

Data Index: 1369526 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8487. Min Act: -0.0000

Data Index: 1389333 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8583. Min Act: -0.0000

Data Index: 485756 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.9246. Min Act: -0.0000

Data Index: 1652179 (Python Code)

Max Activating Token Index: 316

Text #15

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8290. Min Act: -0.0000

Data Index: 1369458 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1605199 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.9058. Min Act: -0.0000

Data Index: 1434611 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.7987. Min Act: -0.0000

Data Index: 1644829 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 2.5508. Min Range: -2.5508

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1533592 (Python Code)

Max Activating Token Index: 843