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

Dataset: The Pile

Neuron 1555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1096861 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1288645 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1645823 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1430752 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1207257 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5441. Min Act: -0.0000

Data Index: 679581 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5115. Min Act: -0.0000

Data Index: 59814 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5274. Min Act: -0.0000

Data Index: 373279 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1394544 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1536653 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5122. Min Act: -0.0000

Data Index: 940855 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4735. Min Act: -0.0000

Data Index: 513825 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4874. Min Act: -0.0000

Data Index: 635880 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4820. Min Act: -0.0000

Data Index: 92680 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1930912 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1713761 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5028. Min Act: -0.0000

Data Index: 980852 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1684535 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4584. Min Act: -0.0000

Data Index: 832146 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1772406 (The Pile)

Max Activating Token Index: 632