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

Dataset: The Pile

Neuron 4013 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: 0.4969. Min Range: -0.4969

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1482440 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1985659 (The Pile)

Max Activating Token Index: 674

Text #2

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4081. Min Act: -0.0000

Data Index: 182201 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1854722 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4969. Min Act: -0.0000

Data Index: 792782 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1485518 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1172422 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1138373 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3536. Min Act: -0.0000

Data Index: 822348 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4375. Min Act: -0.0000

Data Index: 509061 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1281844 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3743. Min Act: -0.0000

Data Index: 290647 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3620. Min Act: 0.0000

Data Index: 1117850 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1703513 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4205. Min Act: -0.0000

Data Index: 276829 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1287426 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1204896 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3347. Min Act: -0.0000

Data Index: 664665 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1877292 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3753. Min Act: -0.0000

Data Index: 366513 (The Pile)

Max Activating Token Index: 777