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

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

Neuron 4923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0002

Data Index: 230890 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0939. Min Act: -0.0002

Data Index: 541433 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1295434 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0801. Min Act: -0.0002

Data Index: 953819 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1042898 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1268074 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0708. Min Act: -0.0002

Data Index: 604355 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1102529 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0686. Min Act: -0.0002

Data Index: 146575 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0699. Min Act: -0.0002

Data Index: 675282 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0696. Min Act: -0.0002

Data Index: 344312 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1058658 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0692. Min Act: -0.0002

Data Index: 516287 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0685. Min Act: -0.0002

Data Index: 330231 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1080223 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0672. Min Act: -0.0002

Data Index: 660226 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1163494 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0638. Min Act: -0.0002

Data Index: 358191 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1335710 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0658. Min Act: -0.0002

Data Index: 565779 (C4 (Web Text))

Max Activating Token Index: 906