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

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

Neuron 4454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.3665. Min Act: -0.0000

Data Index: 79730 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.3180. Min Act: -0.0000

Data Index: 890543 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.3015. Min Act: -0.0001

Data Index: 316803 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1042522 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2813. Min Act: -0.0001

Data Index: 954659 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1043514 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2659. Min Act: -0.0000

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2870. Min Act: -0.0001

Data Index: 357794 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2809. Min Act: -0.0000

Data Index: 687024 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2742. Min Act: -0.0001

Data Index: 772536 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2608. Min Act: -0.0001

Data Index: 826776 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2557. Min Act: -0.0001

Data Index: 372195 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1152448 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2655. Min Act: -0.0000

Data Index: 117173 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2581. Min Act: -0.0001

Data Index: 427803 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2469. Min Act: -0.0001

Data Index: 298355 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2510. Min Act: -0.0001

Data Index: 805067 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2351. Min Act: -0.0001

Data Index: 1227728 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.3665. Min Range: -0.3665

Max Act: 0.2432. Min Act: -0.0001

Data Index: 155297 (C4 (Web Text))

Max Activating Token Index: 288