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

Dataset: The Pile

Neuron 1436 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1878982 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1608618 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3252. Min Act: -0.0000

Data Index: 735646 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1087450 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1975911 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2726. Min Act: -0.0000

Data Index: 115498 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1106649 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2978. Min Act: -0.0000

Data Index: 914434 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2837. Min Act: -0.0000

Data Index: 766311 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1609977 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1533220 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1524969 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1782684 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1316064 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2677. Min Act: -0.0000

Data Index: 483577 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2737. Min Act: -0.0000

Data Index: 831695 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1909953 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1829737 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1183185 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.4402. Min Range: -0.4402

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1885137 (The Pile)

Max Activating Token Index: 798