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

Dataset: The Pile

Neuron 602 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3180. Min Range: -7.3180

Max Act: 7.3180. Min Act: -0.0000

Data Index: 478036 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.9559. Min Act: -0.0000

Data Index: 153630 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 7.3180. Min Range: -7.3180

Max Act: 7.0833. Min Act: -0.0000

Data Index: 898607 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.4817. Min Act: -0.0000

Data Index: 774367 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.5566. Min Act: -0.0000

Data Index: 944017 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.7942. Min Act: -0.0000

Data Index: 1918050 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.7556. Min Act: -0.0000

Data Index: 202917 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.7131. Min Act: -0.0000

Data Index: 1814674 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.9011. Min Act: -0.0000

Data Index: 1269004 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.6741. Min Act: -0.0000

Data Index: 1206771 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.2990. Min Act: -0.0000

Data Index: 1474424 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.3867. Min Act: -0.0000

Data Index: 1191700 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.3852. Min Act: -0.0000

Data Index: 1940716 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.4256. Min Act: -0.0000

Data Index: 1937579 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.4149. Min Act: -0.0000

Data Index: 1925 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.3760. Min Act: -0.0000

Data Index: 1491872 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.3393. Min Act: -0.0000

Data Index: 1524698 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.1237. Min Act: -0.0000

Data Index: 1170897 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.2000. Min Act: -0.0000

Data Index: 505794 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 7.3180. Min Range: -7.3180

Max Act: 6.1994. Min Act: -0.0000

Data Index: 1198991 (The Pile)

Max Activating Token Index: 723