Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1975 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0003

Data Index: 77969 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1002261 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0857. Min Act: -0.0003

Data Index: 152629 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0842. Min Act: -0.0003

Data Index: 862584 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0835. Min Act: -0.0003

Data Index: 461844 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0826. Min Act: -0.0003

Data Index: 456460 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0841. Min Act: -0.0004

Data Index: 533897 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0815. Min Act: -0.0003

Data Index: 109168 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1159742 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0800. Min Act: -0.0003

Data Index: 808091 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0797. Min Act: -0.0003

Data Index: 617466 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0774. Min Act: -0.0003

Data Index: 254483 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0767. Min Act: -0.0003

Data Index: 584484 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0768. Min Act: -0.0003

Data Index: 664001 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1040420 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0759. Min Act: -0.0003

Data Index: 719316 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0728. Min Act: -0.0003

Data Index: 202566 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0756. Min Act: -0.0003

Data Index: 899470 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0769. Min Act: -0.0003

Data Index: 252592 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0760. Min Act: -0.0004

Data Index: 783828 (C4 (Web Text))

Max Activating Token Index: 12