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

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

Neuron 5851 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.8996. Min Act: -0.0000

Data Index: 598416 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2454. Min Act: -0.0000

Data Index: 596507 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2189. Min Act: -0.0000

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5028. Min Act: -0.0000

Data Index: 973518 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2687. Min Act: -0.0000

Data Index: 1225139 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.4293. Min Act: -0.0000

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5197. Min Act: -0.0000

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 4.8996. Min Range: -4.8996

Max Act: 3.9582. Min Act: -0.0000

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2953. Min Act: -0.0000

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.0878. Min Act: -0.0000

Data Index: 854863 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.0914. Min Act: -0.0000

Data Index: 330896 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.1196. Min Act: -0.0000

Data Index: 745956 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2128. Min Act: -0.0000

Data Index: 148772 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.3390. Min Act: -0.0000

Data Index: 512540 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 4.8996. Min Range: -4.8996

Max Act: 3.7442. Min Act: -0.0000

Data Index: 177691 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 4.8996. Min Range: -4.8996

Max Act: 3.9794. Min Act: -0.0000

Data Index: 461814 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.2777. Min Act: -0.0000

Data Index: 248247 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 4.8996. Min Range: -4.8996

Max Act: 3.8906. Min Act: -0.0000

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 4.8996. Min Range: -4.8996

Max Act: 3.9470. Min Act: -0.0000

Data Index: 64447 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.0984. Min Act: -0.0000

Data Index: 889070 (C4 (Web Text))

Max Activating Token Index: 826