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

Dataset: The Pile

Neuron 3437 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: 0.8315. Min Range: -0.8315

Max Act: 0.8216. Min Act: -0.0000

Data Index: 586376 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1917424 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.7544. Min Act: -0.0000

Data Index: 230442 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.7829. Min Act: -0.0000

Data Index: 141201 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1038799 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6130. Min Act: -0.0000

Data Index: 558959 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1014113 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6757. Min Act: -0.0000

Data Index: 735128 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6532. Min Act: -0.0000

Data Index: 508793 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1168453 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1338571 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1184156 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1698375 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1930710 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4367. Min Act: -0.0000

Data Index: 818028 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5082. Min Act: -0.0000

Data Index: 708341 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5025. Min Act: -0.0000

Data Index: 480838 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1526109 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1053524 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1737656 (The Pile)

Max Activating Token Index: 659