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

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

Neuron 4518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.8061. Min Act: -0.0000

Data Index: 290062 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6576. Min Act: -0.0000

Data Index: 795226 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5659. Min Act: -0.0000

Data Index: 656092 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4683. Min Act: -0.0000

Data Index: 629172 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5722. Min Act: -0.0000

Data Index: 356455 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5408. Min Act: -0.0000

Data Index: 571051 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1317006 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1164883 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5513. Min Act: -0.0000

Data Index: 973051 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5328. Min Act: -0.0000

Data Index: 983762 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4997. Min Act: -0.0000

Data Index: 906932 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4788. Min Act: -0.0000

Data Index: 374345 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4902. Min Act: -0.0000

Data Index: 320472 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4772. Min Act: -0.0000

Data Index: 157332 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4481. Min Act: -0.0000

Data Index: 174838 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4786. Min Act: -0.0000

Data Index: 839881 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1075790 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4462. Min Act: -0.0000

Data Index: 554289 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4602. Min Act: -0.0000

Data Index: 261035 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4392. Min Act: -0.0000

Data Index: 446814 (C4 (Web Text))

Max Activating Token Index: 313