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

Dataset: The Pile

Neuron 1457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1633372 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.5061. Min Act: -0.0000

Data Index: 69081 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1349193 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3805. Min Act: -0.0000

Data Index: 127919 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4152. Min Act: -0.0000

Data Index: 1395493 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1800220 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1207288 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3312. Min Act: -0.0000

Data Index: 263417 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1804501 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3750. Min Act: -0.0000

Data Index: 651090 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.5015. Min Act: -0.0000

Data Index: 565843 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3427. Min Act: -0.0000

Data Index: 18089 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1713506 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3356. Min Act: -0.0000

Data Index: 930148 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2735. Min Act: -0.0000

Data Index: 640830 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1042822 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1360724 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3220. Min Act: -0.0000

Data Index: 649038 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3611. Min Act: -0.0000

Data Index: 185871 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1950728 (The Pile)

Max Activating Token Index: 854