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

Dataset: The Pile

Neuron 1728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1592152 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.5052. Min Act: -0.0000

Data Index: 420149 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1365059 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2989. Min Act: -0.0000

Data Index: 197301 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1249607 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.3566. Min Act: -0.0000

Data Index: 560923 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.3230. Min Act: -0.0000

Data Index: 1880651 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2305. Min Act: -0.0000

Data Index: 930134 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2699. Min Act: -0.0000

Data Index: 739071 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2986. Min Act: -0.0000

Data Index: 1199883 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1581. Min Act: -0.0000

Data Index: 184869 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1112277 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2364. Min Act: -0.0000

Data Index: 874379 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1920065 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2298. Min Act: -0.0000

Data Index: 603435 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2242. Min Act: -0.0000

Data Index: 668596 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1095980 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1373. Min Act: -0.0000

Data Index: 475427 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0951. Min Act: -0.0000

Data Index: 616543 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1019370 (The Pile)

Max Activating Token Index: 621