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

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

Neuron 666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0857. Min Act: -0.0006

Data Index: 313099 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0006

Data Index: 854672 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0841. Min Act: -0.0006

Data Index: 1233792 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0765. Min Act: -0.0006

Data Index: 925768 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0676. Min Act: -0.0006

Data Index: 325754 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0732. Min Act: -0.0006

Data Index: 1062516 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0673. Min Act: -0.0006

Data Index: 561 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0674. Min Act: -0.0006

Data Index: 1324560 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0604. Min Act: -0.0006

Data Index: 850535 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0655. Min Act: -0.0006

Data Index: 504257 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0656. Min Act: -0.0006

Data Index: 1193469 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0653. Min Act: -0.0006

Data Index: 241438 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0651. Min Act: -0.0006

Data Index: 285724 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0638. Min Act: -0.0006

Data Index: 1334705 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0639. Min Act: -0.0006

Data Index: 386 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0654. Min Act: -0.0006

Data Index: 236503 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0601. Min Act: -0.0006

Data Index: 1282942 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1225621 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0596. Min Act: -0.0006

Data Index: 941579 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0655. Min Act: -0.0006

Data Index: 1288697 (C4 (Web Text))

Max Activating Token Index: 998