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

Dataset: The Pile

Neuron 111 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: 0.8884. Min Range: -0.8884

Max Act: 0.8884. Min Act: 0.0000

Data Index: 752545 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8076. Min Act: -0.0000

Data Index: 993566 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7051. Min Act: -0.0000

Data Index: 357828 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1722147 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6859. Min Act: -0.0000

Data Index: 141287 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6584. Min Act: -0.0000

Data Index: 346974 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6946. Min Act: -0.0000

Data Index: 208968 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6863. Min Act: -0.0000

Data Index: 205522 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1691948 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1148493 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6515. Min Act: -0.0000

Data Index: 292853 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1399511 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1865727 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1081951 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6466. Min Act: -0.0000

Data Index: 642120 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6253. Min Act: 0.0000

Data Index: 1463805 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5905. Min Act: -0.0000

Data Index: 378596 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1298730 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1239552 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1306800 (The Pile)

Max Activating Token Index: 577