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

Dataset: The Pile

Neuron 5054 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: 0.4238. Min Range: -0.4238

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1724666 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1665795 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1933305 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3410. Min Act: -0.0000

Data Index: 687035 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3740. Min Act: -0.0000

Data Index: 622257 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1416911 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3350. Min Act: -0.0000

Data Index: 32893 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3188. Min Act: -0.0000

Data Index: 697230 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3115. Min Act: -0.0000

Data Index: 811159 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1725255 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1483471 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3156. Min Act: -0.0000

Data Index: 982841 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1965275 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3113. Min Act: -0.0000

Data Index: 201588 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1649543 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1410445 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1304566 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1872658 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1013174 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2877. Min Act: -0.0000

Data Index: 202876 (The Pile)

Max Activating Token Index: 996