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

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

Neuron 2023 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: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0006

Data Index: 354261 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0693. Min Act: -0.0006

Data Index: 204082 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0652. Min Act: -0.0006

Data Index: 849692 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0637. Min Act: -0.0005

Data Index: 1106961 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0670. Min Act: -0.0006

Data Index: 801417 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0627. Min Act: -0.0006

Data Index: 475815 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0639. Min Act: -0.0006

Data Index: 1059609 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0686. Min Act: -0.0005

Data Index: 558493 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0594. Min Act: -0.0005

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0640. Min Act: -0.0006

Data Index: 810521 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0640. Min Act: -0.0006

Data Index: 1252302 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0687. Min Act: -0.0005

Data Index: 558705 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0623. Min Act: -0.0005

Data Index: 719526 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0624. Min Act: -0.0005

Data Index: 647433 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0647. Min Act: -0.0006

Data Index: 290040 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1083921 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0631. Min Act: -0.0006

Data Index: 468803 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0605. Min Act: -0.0006

Data Index: 88630 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0630. Min Act: -0.0006

Data Index: 378739 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0604. Min Act: -0.0005

Data Index: 1241998 (C4 (Web Text))

Max Activating Token Index: 744