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

Dataset: The Pile

Neuron 3445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1065. Min Act: -0.0000

Data Index: 877746 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1696762 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1529890 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1122294 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1150371 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1523286 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0946. Min Act: -0.0000

Data Index: 796658 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0963. Min Act: -0.0000

Data Index: 19536 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1116109 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0909. Min Act: -0.0000

Data Index: 915971 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1726712 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1500144 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0954. Min Act: -0.0000

Data Index: 85237 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1126424 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1862134 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0946. Min Act: -0.0000

Data Index: 498029 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1727969 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0824. Min Act: -0.0000

Data Index: 829424 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1822118 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1098902 (The Pile)

Max Activating Token Index: 288