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

Dataset: The Pile

Neuron 1164 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6744. Min Act: -0.0000

Data Index: 914871 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1800308 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6057. Min Act: -0.0000

Data Index: 487113 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1757188 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6104. Min Act: -0.0000

Data Index: 787560 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1271190 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1937201 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5332. Min Act: -0.0000

Data Index: 564603 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5878. Min Act: -0.0000

Data Index: 950839 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5930. Min Act: -0.0000

Data Index: 182065 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1318474 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5634. Min Act: -0.0000

Data Index: 376511 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1531206 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5411. Min Act: -0.0000

Data Index: 462117 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1214819 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5071. Min Act: -0.0000

Data Index: 995145 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1610450 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5404. Min Act: -0.0000

Data Index: 208225 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1122744 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1934114 (The Pile)

Max Activating Token Index: 393