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

Dataset: The Pile

Neuron 1277 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: 0.5479. Min Range: -0.5479

Max Act: 0.5479. Min Act: -0.0000

Data Index: 864037 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1958013 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1626602 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4348. Min Act: -0.0000

Data Index: 800602 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4336. Min Act: -0.0000

Data Index: 904007 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4331. Min Act: -0.0000

Data Index: 313018 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4296. Min Act: -0.0000

Data Index: 917783 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4149. Min Act: -0.0000

Data Index: 240280 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1666621 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1561291 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4104. Min Act: -0.0000

Data Index: 90726 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1432335 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3927. Min Act: -0.0000

Data Index: 436939 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3706. Min Act: -0.0000

Data Index: 356099 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3813. Min Act: -0.0000

Data Index: 224070 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3840. Min Act: -0.0000

Data Index: 249857 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3756. Min Act: -0.0000

Data Index: 341157 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1737283 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1861783 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.3760. Min Act: -0.0000

Data Index: 815776 (The Pile)

Max Activating Token Index: 757