Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0002

Data Index: 878153 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0770. Min Act: -0.0002

Data Index: 82661 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1076363 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1270878 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1083724 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0701. Min Act: -0.0002

Data Index: 664532 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0689. Min Act: -0.0002

Data Index: 550942 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0670. Min Act: -0.0002

Data Index: 714655 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0677. Min Act: -0.0003

Data Index: 501457 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0667. Min Act: -0.0003

Data Index: 941541 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0677. Min Act: -0.0003

Data Index: 884905 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0676. Min Act: -0.0004

Data Index: 926202 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1159738 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0671. Min Act: -0.0002

Data Index: 133494 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0667. Min Act: -0.0003

Data Index: 135763 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0642. Min Act: -0.0003

Data Index: 9537 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0638. Min Act: -0.0002

Data Index: 285349 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0634. Min Act: -0.0003

Data Index: 92368 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0641. Min Act: -0.0002

Data Index: 394745 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1281518 (C4 (Web Text))

Max Activating Token Index: 396