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

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

Neuron 619 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6918. Min Range: -2.6918

Max Act: 2.6918. Min Act: -0.0000

Data Index: 436576 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.6918. Min Range: -2.6918

Max Act: 2.3432. Min Act: -0.0000

Data Index: 32169 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 2.6918. Min Range: -2.6918

Max Act: 2.2910. Min Act: -0.0000

Data Index: 49761 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 2.6918. Min Range: -2.6918

Max Act: 2.0913. Min Act: -0.0000

Data Index: 77462 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.7942. Min Act: -0.0000

Data Index: 427433 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.8560. Min Act: -0.0000

Data Index: 776808 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.7741. Min Act: -0.0000

Data Index: 376500 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.8351. Min Act: -0.0000

Data Index: 938396 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.6997. Min Act: -0.0000

Data Index: 204001 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1174834 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.5695. Min Act: -0.0000

Data Index: 109080 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.6651. Min Act: -0.0000

Data Index: 819052 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.6211. Min Act: -0.0000

Data Index: 470728 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.4288. Min Act: -0.0000

Data Index: 864377 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.7720. Min Act: -0.0000

Data Index: 675933 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1349349 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.5140. Min Act: -0.0000

Data Index: 604753 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.4888. Min Act: -0.0000

Data Index: 420460 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.3706. Min Act: -0.0000

Data Index: 369877 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 2.6918. Min Range: -2.6918

Max Act: 1.4304. Min Act: -0.0000

Data Index: 265310 (C4 (Web Text))

Max Activating Token Index: 255