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

Dataset: The Pile

Neuron 3706 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: 5.9404. Min Range: -5.9404

Max Act: 5.9404. Min Act: -0.0000

Data Index: 528816 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 5.9404. Min Range: -5.9404

Max Act: 5.1614. Min Act: -0.0000

Data Index: 1639969 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 5.9404. Min Range: -5.9404

Max Act: 5.1035. Min Act: -0.0000

Data Index: 177482 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.8581. Min Act: -0.0000

Data Index: 992833 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.4859. Min Act: -0.0000

Data Index: 1783266 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.8153. Min Act: -0.0000

Data Index: 1758441 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.7431. Min Act: -0.0000

Data Index: 1543205 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.1894. Min Act: -0.0000

Data Index: 510290 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 5.9404. Min Range: -5.9404

Max Act: 3.9853. Min Act: -0.0000

Data Index: 1606305 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.4609. Min Act: -0.0000

Data Index: 1818303 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.4027. Min Act: -0.0000

Data Index: 1982131 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.2854. Min Act: -0.0000

Data Index: 793059 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.0859. Min Act: -0.0000

Data Index: 666783 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.0366. Min Act: -0.0000

Data Index: 1640574 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 5.9404. Min Range: -5.9404

Max Act: 3.9057. Min Act: -0.0000

Data Index: 89887 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.0815. Min Act: -0.0000

Data Index: 1410888 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 5.9404. Min Range: -5.9404

Max Act: 3.8886. Min Act: -0.0000

Data Index: 1119772 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.3269. Min Act: -0.0000

Data Index: 631640 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 5.9404. Min Range: -5.9404

Max Act: 3.2942. Min Act: -0.0000

Data Index: 499455 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 5.9404. Min Range: -5.9404

Max Act: 4.2596. Min Act: -0.0000

Data Index: 1145096 (The Pile)

Max Activating Token Index: 807