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

Dataset: The Pile

Neuron 3986 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1372584 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5668. Min Act: -0.0000

Data Index: 361721 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5709. Min Act: -0.0000

Data Index: 473337 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1999426 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1252341 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5864. Min Act: -0.0000

Data Index: 252157 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1861191 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1145185 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1070891 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5726. Min Act: -0.0000

Data Index: 281340 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4959. Min Act: -0.0000

Data Index: 134500 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1991540 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1205307 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4726. Min Act: -0.0000

Data Index: 322498 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5154. Min Act: -0.0000

Data Index: 593081 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1647916 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4923. Min Act: -0.0000

Data Index: 700907 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4633. Min Act: -0.0000

Data Index: 796363 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1688372 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.6686. Min Range: -0.6686

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1045210 (The Pile)

Max Activating Token Index: 367