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

Dataset: The Pile

Neuron 621 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9083. Min Act: -0.0000

Data Index: 705925 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9026. Min Act: -0.0000

Data Index: 593647 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1514398 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8270. Min Act: -0.0000

Data Index: 532187 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1766291 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1908205 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9046. Min Act: -0.0000

Data Index: 48915 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1654928 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8218. Min Act: -0.0000

Data Index: 835064 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1330940 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8105. Min Act: -0.0000

Data Index: 708094 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7522. Min Act: -0.0000

Data Index: 954449 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8074. Min Act: -0.0000

Data Index: 689618 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7328. Min Act: -0.0000

Data Index: 378490 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1525260 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1590787 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1001402 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1328575 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1473752 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6916. Min Act: -0.0000

Data Index: 816642 (The Pile)

Max Activating Token Index: 975