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

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

Neuron 1237 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: 0.8534. Min Range: -0.8534

Max Act: 0.8534. Min Act: -0.0000

Data Index: 742051 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7290. Min Act: -0.0000

Data Index: 628093 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1115934 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1332626 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6822. Min Act: -0.0000

Data Index: 274900 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6766. Min Act: -0.0000

Data Index: 79075 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1310185 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1337967 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6601. Min Act: -0.0000

Data Index: 510223 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6237. Min Act: -0.0000

Data Index: 212755 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6336. Min Act: -0.0000

Data Index: 319825 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6181. Min Act: -0.0000

Data Index: 813813 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6143. Min Act: -0.0000

Data Index: 502135 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5778. Min Act: -0.0000

Data Index: 582744 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1098002 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6050. Min Act: -0.0000

Data Index: 298627 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5671. Min Act: -0.0000

Data Index: 878896 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5640. Min Act: -0.0000

Data Index: 99501 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5823. Min Act: -0.0000

Data Index: 384435 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5698. Min Act: -0.0000

Data Index: 622493 (C4 (Web Text))

Max Activating Token Index: 901