Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4668 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1401039 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5632. Min Act: -0.0000

Data Index: 615038 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1369592 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1366852 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1556798 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4719. Min Act: -0.0000

Data Index: 205961 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1555567 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4399. Min Act: 0.0000

Data Index: 1017647 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1406722 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4968. Min Act: 0.0000

Data Index: 615682 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1434153 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1560389 (Python Code)

Max Activating Token Index: 197

Text #12

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1377224 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4429. Min Act: -0.0000

Data Index: 511188 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1511182 (Python Code)

Max Activating Token Index: 244

Text #15

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1407855 (Python Code)

Max Activating Token Index: 612

Text #16

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4305. Min Act: -0.0000

Data Index: 799054 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4328. Min Act: 0.0000

Data Index: 1054034 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4076. Min Act: 0.0000

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4207. Min Act: -0.0000

Data Index: 302516 (C4 (Web Text))

Max Activating Token Index: 386