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

Dataset: The Pile

Neuron 3141 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: 1.8668. Min Range: -1.8668

Max Act: 1.8668. Min Act: -0.0000

Data Index: 767101 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1584663 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.7061. Min Act: -0.0000

Data Index: 845600 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.5940. Min Act: -0.0000

Data Index: 252655 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1186945 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1195454 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.2373. Min Act: -0.0000

Data Index: 243955 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1636174 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1947. Min Act: -0.0000

Data Index: 953040 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.2058. Min Act: -0.0000

Data Index: 660981 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1244. Min Act: -0.0000

Data Index: 484624 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1367. Min Act: -0.0000

Data Index: 631720 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1881639 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.1134. Min Act: -0.0000

Data Index: 328642 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0647. Min Act: -0.0000

Data Index: 684704 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0576. Min Act: -0.0000

Data Index: 563494 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0509. Min Act: 0.0000

Data Index: 1277225 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1913700 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0634. Min Act: 0.0000

Data Index: 953435 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 1.8668. Min Range: -1.8668

Max Act: 1.0847. Min Act: -0.0000

Data Index: 140161 (The Pile)

Max Activating Token Index: 1019