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

Dataset: The Pile

Neuron 3705 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6057. Min Range: -5.6057

Max Act: 5.6057. Min Act: -0.0000

Data Index: 823319 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 5.6057. Min Range: -5.6057

Max Act: 5.0328. Min Act: -0.0000

Data Index: 1701412 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.3470. Min Act: -0.0000

Data Index: 504190 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.4158. Min Act: -0.0000

Data Index: 757314 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.0154. Min Act: -0.0000

Data Index: 318514 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.1065. Min Act: -0.0000

Data Index: 1696827 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.1181. Min Act: -0.0000

Data Index: 1575440 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.7583. Min Act: -0.0000

Data Index: 1812713 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.7080. Min Act: -0.0000

Data Index: 1223019 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.1415. Min Act: -0.0000

Data Index: 1011613 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 5.6057. Min Range: -5.6057

Max Act: 4.1447. Min Act: -0.0000

Data Index: 1187545 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.4314. Min Act: -0.0000

Data Index: 1517300 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.5213. Min Act: -0.0000

Data Index: 1754618 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.8925. Min Act: -0.0000

Data Index: 241997 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.8406. Min Act: -0.0000

Data Index: 1112617 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.6742. Min Act: -0.0000

Data Index: 1069800 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.4425. Min Act: -0.0000

Data Index: 1419382 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.4673. Min Act: -0.0000

Data Index: 579561 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.7020. Min Act: -0.0000

Data Index: 1069813 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 5.6057. Min Range: -5.6057

Max Act: 3.7000. Min Act: -0.0000

Data Index: 687852 (The Pile)

Max Activating Token Index: 713