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

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

Neuron 2031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.8540. Min Act: -0.0002

Data Index: 385673 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.6194. Min Act: -0.0002

Data Index: 1304599 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5685. Min Act: -0.0002

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5867. Min Act: -0.0002

Data Index: 747076 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5580. Min Act: -0.0002

Data Index: 668109 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5154. Min Act: -0.0002

Data Index: 1158788 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5487. Min Act: -0.0002

Data Index: 470708 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.2761. Min Act: -0.0002

Data Index: 639017 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5112. Min Act: -0.0002

Data Index: 124660 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5050. Min Act: -0.0002

Data Index: 821043 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4906. Min Act: -0.0002

Data Index: 365677 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4781. Min Act: -0.0002

Data Index: 1015089 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.5526. Min Act: -0.0002

Data Index: 810574 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4256. Min Act: -0.0002

Data Index: 610109 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4099. Min Act: -0.0003

Data Index: 921233 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4121. Min Act: -0.0002

Data Index: 1173114 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4037. Min Act: -0.0002

Data Index: 76016 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4002. Min Act: -0.0002

Data Index: 622564 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.4661. Min Act: -0.0002

Data Index: 837888 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.8540. Min Range: -1.8540

Max Act: 1.3820. Min Act: -0.0002

Data Index: 937278 (C4 (Web Text))

Max Activating Token Index: 968