Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1763 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.3563. Min Act: -0.0000

Data Index: 895508 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.0833. Min Act: -0.0000

Data Index: 1169339 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.0771. Min Act: -0.0000

Data Index: 439833 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9498. Min Act: -0.0000

Data Index: 420816 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.0611. Min Act: -0.0000

Data Index: 895267 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.0553. Min Act: -0.0000

Data Index: 72156 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.3563. Min Range: -2.3563

Max Act: 2.1548. Min Act: -0.0000

Data Index: 843806 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9082. Min Act: -0.0000

Data Index: 749499 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8879. Min Act: -0.0000

Data Index: 357474 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9697. Min Act: -0.0000

Data Index: 1182299 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9463. Min Act: -0.0000

Data Index: 865680 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1007764 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.9054. Min Act: -0.0000

Data Index: 895299 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8570. Min Act: -0.0000

Data Index: 1133123 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8546. Min Act: -0.0000

Data Index: 54467 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8559. Min Act: -0.0000

Data Index: 638642 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8535. Min Act: -0.0000

Data Index: 868225 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.7244. Min Act: -0.0000

Data Index: 715877 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.8090. Min Act: -0.0000

Data Index: 740014 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.3563. Min Range: -2.3563

Max Act: 1.7315. Min Act: -0.0000

Data Index: 337109 (C4 (Web Text))

Max Activating Token Index: 950