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

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

Neuron 2685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3539. Min Act: -0.0000

Data Index: 432103 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3590. Min Act: -0.0000

Data Index: 377986 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3451. Min Act: -0.0000

Data Index: 12273 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3270. Min Act: -0.0000

Data Index: 436970 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3104. Min Act: -0.0000

Data Index: 779520 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1014391 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3044. Min Act: -0.0000

Data Index: 266219 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2819. Min Act: -0.0000

Data Index: 865418 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2792. Min Act: -0.0000

Data Index: 733920 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2790. Min Act: -0.0000

Data Index: 770315 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2728. Min Act: -0.0000

Data Index: 864608 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2564. Min Act: -0.0000

Data Index: 9409 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2687. Min Act: -0.0000

Data Index: 138057 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2589. Min Act: -0.0000

Data Index: 58870 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2605. Min Act: -0.0000

Data Index: 588631 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2592. Min Act: -0.0000

Data Index: 651478 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2650. Min Act: -0.0000

Data Index: 387861 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2447. Min Act: -0.0000

Data Index: 160994 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1215864 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2340. Min Act: -0.0000

Data Index: 218764 (C4 (Web Text))

Max Activating Token Index: 203