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

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

Neuron 1646 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: 2.1667. Min Range: -2.1667

Max Act: 2.1652. Min Act: -0.0000

Data Index: 1272680 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 2.1667. Min Range: -2.1667

Max Act: 2.1667. Min Act: -0.0000

Data Index: 558392 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.7780. Min Act: -0.0000

Data Index: 1203468 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.6639. Min Act: -0.0000

Data Index: 1209749 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.6771. Min Act: 0.0001

Data Index: 1127858 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.5599. Min Act: -0.0000

Data Index: 451051 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1295123 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1129896 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.4761. Min Act: -0.0000

Data Index: 100357 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.4090. Min Act: -0.0000

Data Index: 892595 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.4824. Min Act: -0.0000

Data Index: 83494 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.4042. Min Act: -0.0000

Data Index: 584145 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.3918. Min Act: -0.0000

Data Index: 175889 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.3033. Min Act: -0.0000

Data Index: 740093 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.2153. Min Act: 0.0000

Data Index: 1251136 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.2751. Min Act: -0.0000

Data Index: 957932 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.3146. Min Act: -0.0000

Data Index: 334465 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1133444 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1111504 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 2.1667. Min Range: -2.1667

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1282546 (C4 (Web Text))

Max Activating Token Index: 893