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

Dataset: The Pile

Neuron 1567 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: 0.3896. Min Range: -0.3896

Max Act: 0.3896. Min Act: 0.0000

Data Index: 593611 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1969664 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3398. Min Act: 0.0000

Data Index: 1228745 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3398. Min Act: -0.0000

Data Index: 439698 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3084. Min Act: 0.0000

Data Index: 750842 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2951. Min Act: 0.0000

Data Index: 1964083 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1331000 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3329. Min Act: -0.0000

Data Index: 353893 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2918. Min Act: -0.0000

Data Index: 549230 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1549792 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1310033 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1257466 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1592923 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3134. Min Act: -0.0000

Data Index: 884534 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2940. Min Act: 0.0000

Data Index: 1485102 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3189. Min Act: -0.0000

Data Index: 237413 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1709476 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3178. Min Act: -0.0000

Data Index: 404573 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2967. Min Act: 0.0000

Data Index: 521809 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3020. Min Act: 0.0000

Data Index: 509437 (The Pile)

Max Activating Token Index: 288