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

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

Neuron 1605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.8755. Min Act: -0.0000

Data Index: 662539 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.8167. Min Act: -0.0000

Data Index: 608868 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.7805. Min Act: -0.0000

Data Index: 797317 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.7768. Min Act: -0.0000

Data Index: 929059 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.7518. Min Act: -0.0000

Data Index: 619511 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.7689. Min Act: -0.0000

Data Index: 236932 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6935. Min Act: -0.0000

Data Index: 795664 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6608. Min Act: -0.0000

Data Index: 93728 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6030. Min Act: -0.0000

Data Index: 709658 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1057889 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5761. Min Act: 0.0000

Data Index: 890036 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5769. Min Act: -0.0000

Data Index: 294350 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1016252 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5492. Min Act: -0.0000

Data Index: 358402 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5601. Min Act: -0.0000

Data Index: 473656 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1120247 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5355. Min Act: -0.0000

Data Index: 487986 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5382. Min Act: -0.0000

Data Index: 831027 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5697. Min Act: -0.0000

Data Index: 667444 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5504. Min Act: -0.0000

Data Index: 306347 (C4 (Web Text))

Max Activating Token Index: 863