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

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

Neuron 3682 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: 0.0916. Min Range: -0.0916

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1166033 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0813. Min Act: -0.0002

Data Index: 814534 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1048021 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0800. Min Act: -0.0002

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0744. Min Act: -0.0003

Data Index: 121545 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0715. Min Act: -0.0003

Data Index: 500945 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1143700 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0690. Min Act: -0.0002

Data Index: 763325 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0635. Min Act: -0.0002

Data Index: 933059 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0691. Min Act: -0.0002

Data Index: 399065 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0731. Min Act: -0.0002

Data Index: 386109 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0774. Min Act: -0.0002

Data Index: 272438 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0696. Min Act: -0.0002

Data Index: 878470 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0678. Min Act: -0.0003

Data Index: 878678 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1085369 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0656. Min Act: -0.0002

Data Index: 663079 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0656. Min Act: -0.0002

Data Index: 243915 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0678. Min Act: -0.0003

Data Index: 216106 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1434432 (Python Code)

Max Activating Token Index: 217