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

Dataset: The Pile

Neuron 3206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0970. Min Act: -0.0003

Data Index: 400583 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0964. Min Act: -0.0003

Data Index: 1491097 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0963. Min Act: -0.0003

Data Index: 550132 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0003

Data Index: 364800 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1601756 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0894. Min Act: -0.0003

Data Index: 77575 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0881. Min Act: -0.0002

Data Index: 627649 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0853. Min Act: -0.0003

Data Index: 930428 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0841. Min Act: -0.0003

Data Index: 208629 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1696160 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1314268 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1181866 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0883. Min Act: -0.0003

Data Index: 266124 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0815. Min Act: -0.0003

Data Index: 427629 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0785. Min Act: -0.0003

Data Index: 380879 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1018428 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1857462 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0818. Min Act: -0.0003

Data Index: 867297 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1848891 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0793. Min Act: -0.0003

Data Index: 1731330 (The Pile)

Max Activating Token Index: 742