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

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

Neuron 5422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6826. Min Act: -0.0002

Data Index: 312939 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6625. Min Act: -0.0002

Data Index: 1086248 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6495. Min Act: -0.0002

Data Index: 793357 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6629. Min Act: -0.0002

Data Index: 762990 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6214. Min Act: -0.0002

Data Index: 225142 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6346. Min Act: -0.0002

Data Index: 999226 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6171. Min Act: -0.0002

Data Index: 1313882 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6148. Min Act: -0.0002

Data Index: 640596 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6238. Min Act: -0.0002

Data Index: 76776 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6183. Min Act: -0.0002

Data Index: 1205881 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6049. Min Act: -0.0003

Data Index: 1358281 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6140. Min Act: -0.0002

Data Index: 247423 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6000. Min Act: -0.0002

Data Index: 1316186 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5898. Min Act: -0.0002

Data Index: 593486 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5902. Min Act: -0.0002

Data Index: 786893 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5914. Min Act: -0.0002

Data Index: 215983 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5927. Min Act: -0.0002

Data Index: 1171342 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5868. Min Act: -0.0002

Data Index: 647777 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5867. Min Act: -0.0002

Data Index: 1086113 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5853. Min Act: -0.0002

Data Index: 470907 (C4 (Web Text))

Max Activating Token Index: 838