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

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

Neuron 1551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.8077. Min Act: -0.0000

Data Index: 375451 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.5796. Min Act: -0.0000

Data Index: 959420 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.6778. Min Act: -0.0000

Data Index: 818655 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.5536. Min Act: -0.0000

Data Index: 833722 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.2434. Min Act: -0.0000

Data Index: 414540 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.3253. Min Act: -0.0000

Data Index: 569503 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.2939. Min Act: -0.0000

Data Index: 353623 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.2688. Min Act: -0.0000

Data Index: 81941 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.5284. Min Act: -0.0000

Data Index: 1024315 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.3811. Min Act: -0.0000

Data Index: 72249 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.3463. Min Act: -0.0000

Data Index: 1231675 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.2049. Min Act: -0.0000

Data Index: 68781 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 2.8077. Min Range: -2.8077

Max Act: 1.9408. Min Act: -0.0000

Data Index: 965421 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.0470. Min Act: -0.0000

Data Index: 103739 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.1090. Min Act: -0.0000

Data Index: 865691 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.8077. Min Range: -2.8077

Max Act: 1.9848. Min Act: -0.0000

Data Index: 128926 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.2178. Min Act: -0.0000

Data Index: 858406 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.0934. Min Act: 0.0000

Data Index: 46887 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.8077. Min Range: -2.8077

Max Act: 2.1618. Min Act: -0.0000

Data Index: 441928 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.8077. Min Range: -2.8077

Max Act: 1.9314. Min Act: -0.0000

Data Index: 390673 (C4 (Web Text))

Max Activating Token Index: 677