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

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

Neuron 1762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6779. Min Act: -0.0000

Data Index: 603797 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1159598 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1162004 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5802. Min Act: -0.0000

Data Index: 73467 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5825. Min Act: -0.0000

Data Index: 549388 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5702. Min Act: -0.0000

Data Index: 254261 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5657. Min Act: -0.0000

Data Index: 306494 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1321930 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1153924 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5510. Min Act: -0.0000

Data Index: 170429 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5240. Min Act: -0.0000

Data Index: 571150 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1031964 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5095. Min Act: -0.0000

Data Index: 28049 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5432. Min Act: -0.0000

Data Index: 421874 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4794. Min Act: -0.0000

Data Index: 245340 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4791. Min Act: -0.0000

Data Index: 433868 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4809. Min Act: -0.0000

Data Index: 880627 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1159882 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5100. Min Act: -0.0000

Data Index: 353100 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4503. Min Act: -0.0000

Data Index: 93292 (C4 (Web Text))

Max Activating Token Index: 275