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

Dataset: The Pile

Neuron 960 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: 3.8556. Min Range: -3.8556

Max Act: 3.4162. Min Act: -0.0000

Data Index: 1239032 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.8556. Min Act: -0.0000

Data Index: 998714 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.0274. Min Act: -0.0000

Data Index: 587025 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.1820. Min Act: -0.0000

Data Index: 757998 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.0550. Min Act: -0.0000

Data Index: 1612209 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.0388. Min Act: -0.0000

Data Index: 1629375 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1623600 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.1240. Min Act: -0.0000

Data Index: 1175163 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.8156. Min Act: -0.0000

Data Index: 1213837 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.9369. Min Act: -0.0000

Data Index: 1196441 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 3.8556. Min Range: -3.8556

Max Act: 3.0756. Min Act: -0.0000

Data Index: 1536067 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.9023. Min Act: -0.0000

Data Index: 612631 (The Pile)

Max Activating Token Index: 320

Text #12

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.3154. Min Act: -0.0000

Data Index: 381368 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.6611. Min Act: -0.0000

Data Index: 602675 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.3034. Min Act: -0.0000

Data Index: 116925 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.2804. Min Act: -0.0000

Data Index: 15517 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.2791. Min Act: -0.0000

Data Index: 1538427 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.3394. Min Act: -0.0000

Data Index: 651670 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.3104. Min Act: -0.0000

Data Index: 1072516 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 3.8556. Min Range: -3.8556

Max Act: 2.3915. Min Act: -0.0000

Data Index: 1773133 (The Pile)

Max Activating Token Index: 853