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

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

Neuron 1940 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.7766. Min Act: -0.0001

Data Index: 367624 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.5420. Min Act: -0.0001

Data Index: 222938 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.3169. Min Act: -0.0001

Data Index: 241413 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.3290. Min Act: -0.0001

Data Index: 908219 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.3410. Min Act: -0.0001

Data Index: 1321187 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.2887. Min Act: -0.0001

Data Index: 520100 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.2372. Min Act: -0.0001

Data Index: 400229 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.3877. Min Act: -0.0001

Data Index: 752765 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.2073. Min Act: -0.0001

Data Index: 612384 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.1945. Min Act: -0.0001

Data Index: 614161 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1191014 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.2974. Min Act: -0.0001

Data Index: 640823 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.1720. Min Act: -0.0001

Data Index: 334831 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.1608. Min Act: -0.0001

Data Index: 443866 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.2361. Min Act: -0.0001

Data Index: 576642 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.0937. Min Act: -0.0001

Data Index: 360085 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.0995. Min Act: -0.0001

Data Index: 278082 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.0632. Min Act: -0.0001

Data Index: 832561 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.1157. Min Act: -0.0001

Data Index: 793928 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.7766. Min Range: -1.7766

Max Act: 1.1704. Min Act: -0.0001

Data Index: 584017 (C4 (Web Text))

Max Activating Token Index: 610