Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.6428. Min Act: -0.0005

Data Index: 169282 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.6089. Min Act: -0.0005

Data Index: 409256 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4760. Min Act: -0.0005

Data Index: 1312608 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5685. Min Act: -0.0005

Data Index: 1204695 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4920. Min Act: -0.0005

Data Index: 542392 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4781. Min Act: -0.0005

Data Index: 1322982 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4752. Min Act: -0.0005

Data Index: 263424 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4931. Min Act: -0.0005

Data Index: 1176469 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4660. Min Act: -0.0005

Data Index: 1331232 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4636. Min Act: -0.0005

Data Index: 1144795 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4807. Min Act: -0.0005

Data Index: 1052086 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4544. Min Act: -0.0005

Data Index: 677216 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4843. Min Act: -0.0005

Data Index: 969577 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4507. Min Act: -0.0005

Data Index: 541677 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4461. Min Act: -0.0005

Data Index: 388033 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4468. Min Act: -0.0005

Data Index: 54428 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4270. Min Act: -0.0005

Data Index: 226447 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.3620. Min Act: -0.0005

Data Index: 1067893 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4615. Min Act: -0.0005

Data Index: 1345794 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4551. Min Act: -0.0005

Data Index: 199184 (C4 (Web Text))

Max Activating Token Index: 315