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

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

Neuron 2610 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: 1.0509. Min Range: -1.0509

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1632085 (Python Code)

Max Activating Token Index: 877

Text #1

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1426482 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1156728 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8245. Min Act: -0.0000

Data Index: 615598 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7930. Min Act: -0.0000

Data Index: 353867 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1377802 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1325333 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7540. Min Act: -0.0000

Data Index: 949638 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7019. Min Act: -0.0000

Data Index: 942058 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1486641 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1593348 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6898. Min Act: -0.0000

Data Index: 512317 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1643511 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1443360 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1100554 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1628748 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1044715 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1463434 (Python Code)

Max Activating Token Index: 422

Text #18

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1221719 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1575179 (Python Code)

Max Activating Token Index: 692