Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9655. Min Act: -0.0000

Data Index: 966047 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1232439 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9472. Min Act: -0.0000

Data Index: 772552 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9849. Min Act: -0.0000

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8489. Min Act: -0.0000

Data Index: 336228 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8127. Min Act: -0.0000

Data Index: 916517 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8918. Min Act: -0.0000

Data Index: 298419 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7459. Min Act: -0.0000

Data Index: 644529 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8870. Min Act: -0.0000

Data Index: 520488 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1215859 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8119. Min Act: -0.0000

Data Index: 33276 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6855. Min Act: -0.0000

Data Index: 75126 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6940. Min Act: -0.0000

Data Index: 254796 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7448. Min Act: -0.0000

Data Index: 58558 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6954. Min Act: -0.0000

Data Index: 215539 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7471. Min Act: -0.0000

Data Index: 477444 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6678. Min Act: -0.0000

Data Index: 815350 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6786. Min Act: -0.0000

Data Index: 392484 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6707. Min Act: -0.0000

Data Index: 977558 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7093. Min Act: -0.0000

Data Index: 754846 (C4 (Web Text))

Max Activating Token Index: 65