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

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

Neuron 3470 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7498. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7651. Min Act: -0.0000

Data Index: 650789 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1208529 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6797. Min Act: -0.0000

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6727. Min Act: -0.0000

Data Index: 919601 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6156. Min Act: -0.0000

Data Index: 889746 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5549. Min Act: -0.0000

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5553. Min Act: -0.0000

Data Index: 902475 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5960. Min Act: -0.0000

Data Index: 493281 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5523. Min Act: -0.0000

Data Index: 119341 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5648. Min Act: -0.0000

Data Index: 644794 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5660. Min Act: -0.0000

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1285316 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1346750 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5551. Min Act: -0.0000

Data Index: 860574 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5018. Min Act: -0.0000

Data Index: 870657 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5308. Min Act: -0.0000

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5374. Min Act: -0.0000

Data Index: 207022 (C4 (Web Text))

Max Activating Token Index: 175