Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1767633 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1646656 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1821404 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1099559 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3714. Min Act: -0.0000

Data Index: 546284 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3254. Min Act: -0.0000

Data Index: 624547 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3707. Min Act: -0.0000

Data Index: 666321 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.4015. Min Act: -0.0000

Data Index: 423542 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3688. Min Act: -0.0000

Data Index: 558308 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3826. Min Act: -0.0000

Data Index: 94923 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1119860 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3632. Min Act: -0.0000

Data Index: 284232 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1172133 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3757. Min Act: -0.0000

Data Index: 222269 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3828. Min Act: -0.0000

Data Index: 39624 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1503451 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3377. Min Act: -0.0000

Data Index: 365229 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1354520 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3733. Min Act: -0.0000

Data Index: 767614 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3694. Min Act: -0.0000

Data Index: 356494 (The Pile)

Max Activating Token Index: 528