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

Dataset: The Pile

Neuron 504 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5859. Min Act: -0.0000

Data Index: 949727 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5528. Min Act: -0.0000

Data Index: 103944 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1831140 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1195719 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5422. Min Act: -0.0000

Data Index: 670901 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1698227 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4775. Min Act: 0.0000

Data Index: 505092 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.5024. Min Act: -0.0000

Data Index: 928702 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4434. Min Act: -0.0000

Data Index: 35623 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4339. Min Act: 0.0000

Data Index: 974727 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1314332 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4197. Min Act: -0.0000

Data Index: 423599 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4497. Min Act: -0.0000

Data Index: 406112 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4370. Min Act: -0.0000

Data Index: 247336 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3827. Min Act: -0.0000

Data Index: 269782 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3404. Min Act: -0.0000

Data Index: 605016 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3973. Min Act: -0.0000

Data Index: 761730 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1604040 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.4225. Min Act: -0.0000

Data Index: 618131 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.5859. Min Range: -0.5859

Max Act: 0.3953. Min Act: -0.0000

Data Index: 619537 (The Pile)

Max Activating Token Index: 757