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

Dataset: The Pile

Neuron 361 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: 1.0256. Min Range: -1.0256

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1274848 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1376645 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7893. Min Act: -0.0000

Data Index: 979237 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7952. Min Act: -0.0000

Data Index: 721353 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.8061. Min Act: -0.0000

Data Index: 298448 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1900072 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6540. Min Act: -0.0000

Data Index: 855704 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6832. Min Act: -0.0000

Data Index: 900978 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7191. Min Act: -0.0000

Data Index: 243956 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1306998 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1646845 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6457. Min Act: -0.0000

Data Index: 520600 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6025. Min Act: -0.0000

Data Index: 313706 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6399. Min Act: -0.0000

Data Index: 499051 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1117790 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1263834 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6539. Min Act: -0.0000

Data Index: 679916 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6427. Min Act: -0.0000

Data Index: 443781 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1392608 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 1.0256. Min Range: -1.0256

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1773061 (The Pile)

Max Activating Token Index: 931