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

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

Neuron 2421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3588. Min Act: -0.0000

Data Index: 851236 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3448. Min Act: -0.0000

Data Index: 111034 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3284. Min Act: -0.0000

Data Index: 981240 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2970. Min Act: -0.0000

Data Index: 995698 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1354327 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1083489 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2858. Min Act: -0.0000

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2735. Min Act: -0.0000

Data Index: 129813 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2683. Min Act: -0.0000

Data Index: 964778 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2704. Min Act: -0.0000

Data Index: 988054 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2718. Min Act: -0.0000

Data Index: 893805 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1641805 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2817. Min Act: -0.0000

Data Index: 522820 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2493. Min Act: -0.0000

Data Index: 792168 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2542. Min Act: -0.0000

Data Index: 513998 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2712. Min Act: -0.0000

Data Index: 769277 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2801. Min Act: -0.0000

Data Index: 324238 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2693. Min Act: -0.0000

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2529. Min Act: -0.0000

Data Index: 291964 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2623. Min Act: -0.0000

Data Index: 730356 (C4 (Web Text))

Max Activating Token Index: 890