Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3747. Min Act: -0.0000

Data Index: 803699 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3995. Min Act: -0.0000

Data Index: 479082 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1066650 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3351. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3311. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1168719 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3489. Min Act: -0.0000

Data Index: 750903 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3260. Min Act: -0.0000

Data Index: 92496 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1694242 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1767545 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1036014 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3244. Min Act: -0.0000

Data Index: 789130 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2803. Min Act: -0.0000

Data Index: 374867 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1147545 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3069. Min Act: -0.0000

Data Index: 955680 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1000217 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3079. Min Act: -0.0000

Data Index: 834266 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3317. Min Act: -0.0000

Data Index: 349877 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1216924 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1085779 (The Pile)

Max Activating Token Index: 35