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

Dataset: The Pile

Neuron 988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1193076 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1846888 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1911838 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1537423 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5602. Min Act: -0.0000

Data Index: 798895 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1552564 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1816463 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5304. Min Act: -0.0000

Data Index: 821608 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5058. Min Act: -0.0000

Data Index: 847903 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1649158 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5134. Min Act: -0.0000

Data Index: 131051 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1234907 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4950. Min Act: -0.0000

Data Index: 911846 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5043. Min Act: -0.0000

Data Index: 792754 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4579. Min Act: -0.0000

Data Index: 371041 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.5218. Min Act: -0.0000

Data Index: 537146 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4660. Min Act: -0.0000

Data Index: 983865 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4596. Min Act: -0.0000

Data Index: 547229 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4688. Min Act: -0.0000

Data Index: 514767 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.6500. Min Range: -0.6500

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1156139 (The Pile)

Max Activating Token Index: 596