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

Dataset: The Pile

Neuron 208 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: 0.7076. Min Range: -0.7076

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1684458 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6460. Min Act: -0.0000

Data Index: 144753 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1034586 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6344. Min Act: 0.0000

Data Index: 1807167 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1271465 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6042. Min Act: -0.0000

Data Index: 534478 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1548019 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1277471 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5965. Min Act: -0.0000

Data Index: 574572 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1522624 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5732. Min Act: -0.0000

Data Index: 984945 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5830. Min Act: -0.0000

Data Index: 54503 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5651. Min Act: -0.0000

Data Index: 341652 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1240979 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1188922 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5588. Min Act: -0.0000

Data Index: 805181 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1100741 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5547. Min Act: 0.0000

Data Index: 1113122 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1554745 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1598957 (The Pile)

Max Activating Token Index: 717