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

Dataset: The Pile

Neuron 3023 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: 1.9545. Min Range: -1.9545

Max Act: 1.8887. Min Act: -0.0000

Data Index: 798802 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.9545. Min Act: -0.0000

Data Index: 975687 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7532. Min Act: -0.0000

Data Index: 1163925 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1070928 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1665968 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1904916 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7832. Min Act: -0.0000

Data Index: 361954 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7895. Min Act: -0.0000

Data Index: 903688 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.8441. Min Act: -0.0000

Data Index: 445774 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.7044. Min Act: -0.0000

Data Index: 299518 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.6179. Min Act: -0.0000

Data Index: 295465 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1934284 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.6761. Min Act: -0.0000

Data Index: 223753 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.5722. Min Act: -0.0000

Data Index: 130987 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1806157 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.5429. Min Act: -0.0000

Data Index: 796719 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1224641 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.5634. Min Act: -0.0000

Data Index: 536294 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1486894 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 1.9545. Min Range: -1.9545

Max Act: 1.4694. Min Act: -0.0000

Data Index: 873384 (The Pile)

Max Activating Token Index: 495