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

Dataset: The Pile

Neuron 3048 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3774. Min Act: -0.0000

Data Index: 790009 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2576. Min Act: -0.0000

Data Index: 464571 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1002370 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2701. Min Act: -0.0000

Data Index: 299091 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1149270 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2420. Min Act: -0.0000

Data Index: 662987 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2404. Min Act: -0.0000

Data Index: 482180 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1637435 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1109865 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1695054 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1086882 (The Pile)

Max Activating Token Index: 328

Text #11

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1521190 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1843. Min Act: -0.0000

Data Index: 771892 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2057. Min Act: -0.0000

Data Index: 843950 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1839624 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1896. Min Act: -0.0000

Data Index: 619784 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1711395 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1707. Min Act: -0.0000

Data Index: 777332 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1761. Min Act: -0.0000

Data Index: 753218 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1761087 (The Pile)

Max Activating Token Index: 79