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

Dataset: The Pile

Neuron 2534 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: 0.4782. Min Range: -0.4782

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1170947 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3962. Min Act: -0.0000

Data Index: 156682 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1680487 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3512. Min Act: -0.0000

Data Index: 771680 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1939950 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3117. Min Act: -0.0000

Data Index: 110626 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3148. Min Act: -0.0000

Data Index: 21761 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3157. Min Act: -0.0000

Data Index: 488626 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3321. Min Act: -0.0000

Data Index: 776901 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1875011 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1707784 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1209958 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3707. Min Act: -0.0000

Data Index: 914016 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3035. Min Act: -0.0000

Data Index: 153677 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1387839 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1433167 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1538423 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1456023 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1398098 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1254502 (The Pile)

Max Activating Token Index: 572