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

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

Neuron 3662 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1111. Min Range: -4.1111

Max Act: 4.1111. Min Act: -0.0001

Data Index: 336257 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.9483. Min Act: -0.0001

Data Index: 1159047 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.8472. Min Act: -0.0001

Data Index: 628099 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.8476. Min Act: -0.0001

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.7109. Min Act: -0.0001

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.6866. Min Act: -0.0001

Data Index: 934303 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.5713. Min Act: -0.0001

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.4263. Min Act: -0.0001

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.7221. Min Act: -0.0001

Data Index: 247957 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.3987. Min Act: -0.0001

Data Index: 535750 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.6630. Min Act: -0.0001

Data Index: 773783 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.1931. Min Act: -0.0001

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.4873. Min Act: -0.0001

Data Index: 133604 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.1492. Min Act: -0.0001

Data Index: 687732 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.4435. Min Act: -0.0001

Data Index: 664698 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.2587. Min Act: -0.0001

Data Index: 200886 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.3468. Min Act: -0.0001

Data Index: 649781 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.3473. Min Act: -0.0001

Data Index: 11185 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.3508. Min Act: -0.0001

Data Index: 727557 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 4.1111. Min Range: -4.1111

Max Act: 3.0875. Min Act: -0.0001

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 564