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

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

Neuron 49 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: 0.8260. Min Range: -0.8260

Max Act: 0.8260. Min Act: -0.0002

Data Index: 321842 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.8132. Min Act: -0.0002

Data Index: 1242971 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7794. Min Act: -0.0002

Data Index: 678255 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7626. Min Act: -0.0002

Data Index: 162751 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7676. Min Act: -0.0002

Data Index: 1067902 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7264. Min Act: -0.0002

Data Index: 401596 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7303. Min Act: -0.0002

Data Index: 629572 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7057. Min Act: -0.0002

Data Index: 1112934 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7029. Min Act: -0.0002

Data Index: 49653 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7052. Min Act: -0.0002

Data Index: 291138 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6955. Min Act: -0.0002

Data Index: 656672 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7108. Min Act: -0.0002

Data Index: 510572 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6899. Min Act: -0.0002

Data Index: 598196 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6804. Min Act: -0.0002

Data Index: 450079 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6905. Min Act: -0.0002

Data Index: 556571 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6810. Min Act: -0.0002

Data Index: 469316 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6843. Min Act: -0.0002

Data Index: 523273 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6779. Min Act: -0.0002

Data Index: 546099 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6662. Min Act: -0.0002

Data Index: 54350 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6778. Min Act: -0.0003

Data Index: 137294 (C4 (Web Text))

Max Activating Token Index: 908