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

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

Neuron 4484 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7516. Min Act: -0.0000

Data Index: 123277 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6315. Min Act: 0.0000

Data Index: 191895 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1212032 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5138. Min Act: 0.0001

Data Index: 751599 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1020935 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5167. Min Act: -0.0000

Data Index: 532750 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5268. Min Act: -0.0000

Data Index: 141046 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4948. Min Act: -0.0000

Data Index: 528951 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4741. Min Act: 0.0001

Data Index: 517577 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4866. Min Act: -0.0000

Data Index: 91899 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4960. Min Act: 0.0000

Data Index: 640558 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4621. Min Act: 0.0000

Data Index: 1222081 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4743. Min Act: -0.0000

Data Index: 350041 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4863. Min Act: -0.0000

Data Index: 345467 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4633. Min Act: -0.0000

Data Index: 916672 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4483. Min Act: 0.0001

Data Index: 1088264 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4654. Min Act: -0.0000

Data Index: 37492 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4609. Min Act: -0.0000

Data Index: 334111 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1072386 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4591. Min Act: 0.0000

Data Index: 979979 (C4 (Web Text))

Max Activating Token Index: 166