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

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

Neuron 1645 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0648. Min Act: -0.0002

Data Index: 756856 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 942131 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0591. Min Act: -0.0002

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0592. Min Act: -0.0002

Data Index: 294481 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0643. Min Act: -0.0002

Data Index: 947274 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0593. Min Act: -0.0002

Data Index: 327837 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0577. Min Act: -0.0002

Data Index: 13099 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0531. Min Act: -0.0002

Data Index: 423030 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1588008 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0526. Min Act: -0.0002

Data Index: 472434 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0501. Min Act: -0.0002

Data Index: 269836 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0500. Min Act: -0.0002

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0537. Min Act: -0.0002

Data Index: 629735 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1031547 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1002642 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0539. Min Act: -0.0002

Data Index: 728649 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1016343 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0510. Min Act: -0.0002

Data Index: 147877 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0495. Min Act: -0.0002

Data Index: 500102 (C4 (Web Text))

Max Activating Token Index: 44