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

Dataset: The Pile

Neuron 1999 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: 0.8864. Min Range: -0.8864

Max Act: 0.8864. Min Act: -0.0000

Data Index: 898280 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7451. Min Act: -0.0000

Data Index: 36104 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1595653 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6335. Min Act: -0.0000

Data Index: 489703 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1176440 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6610. Min Act: -0.0000

Data Index: 595811 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1042991 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6595. Min Act: -0.0000

Data Index: 461871 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6549. Min Act: -0.0000

Data Index: 564002 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7418. Min Act: -0.0000

Data Index: 351882 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1027147 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1210967 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1826697 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1613447 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1668551 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5862. Min Act: -0.0000

Data Index: 376493 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1726759 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6154. Min Act: -0.0000

Data Index: 759882 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1634193 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6507. Min Act: -0.0000

Data Index: 730469 (The Pile)

Max Activating Token Index: 821