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

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

Neuron 665 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: 2.1530. Min Range: -2.1530

Max Act: 2.0936. Min Act: -0.0000

Data Index: 437058 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.1530. Min Range: -2.1530

Max Act: 2.1530. Min Act: -0.0000

Data Index: 683393 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.8977. Min Act: -0.0000

Data Index: 796039 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 2.1530. Min Range: -2.1530

Max Act: 2.0499. Min Act: -0.0000

Data Index: 971995 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.8340. Min Act: -0.0000

Data Index: 26838 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.9117. Min Act: -0.0000

Data Index: 34642 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.7127. Min Act: -0.0000

Data Index: 230676 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.8038. Min Act: -0.0000

Data Index: 1322086 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1298151 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1122778 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6795. Min Act: -0.0000

Data Index: 91020 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5667. Min Act: -0.0000

Data Index: 115233 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5330. Min Act: -0.0000

Data Index: 586666 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6249. Min Act: -0.0000

Data Index: 202251 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5720. Min Act: -0.0000

Data Index: 763473 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5053. Min Act: -0.0000

Data Index: 452657 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5925. Min Act: -0.0000

Data Index: 394524 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1118804 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4710. Min Act: -0.0000

Data Index: 901012 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4635. Min Act: -0.0000

Data Index: 213373 (C4 (Web Text))

Max Activating Token Index: 188