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

Dataset: The Pile

Neuron 3856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1395644 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7260. Min Act: -0.0000

Data Index: 885203 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7000. Min Act: -0.0000

Data Index: 783688 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8237. Min Act: -0.0000

Data Index: 29841 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7193. Min Act: -0.0000

Data Index: 63146 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7223. Min Act: -0.0000

Data Index: 108377 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6148. Min Act: -0.0000

Data Index: 947187 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1381507 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1040756 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1161432 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7223. Min Act: -0.0000

Data Index: 834468 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6170. Min Act: -0.0000

Data Index: 543578 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1238942 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5666. Min Act: -0.0000

Data Index: 972102 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1968191 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5014. Min Act: -0.0000

Data Index: 177707 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1969406 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1275147 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.4554. Min Act: -0.0000

Data Index: 976945 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1400922 (The Pile)

Max Activating Token Index: 535