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

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

Neuron 736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3773. Min Range: -6.3773

Max Act: 6.3773. Min Act: -0.0000

Data Index: 529908 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.9110. Min Act: -0.0000

Data Index: 881237 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.5440. Min Act: -0.0000

Data Index: 1177718 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.4559. Min Act: -0.0000

Data Index: 1002850 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.2989. Min Act: -0.0000

Data Index: 131325 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.3413. Min Act: -0.0000

Data Index: 996399 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.0519. Min Act: -0.0000

Data Index: 234658 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.9334. Min Act: -0.0000

Data Index: 335168 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.8734. Min Act: -0.0000

Data Index: 366721 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.6580. Min Act: -0.0000

Data Index: 810979 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 6.3773. Min Range: -6.3773

Max Act: 5.0207. Min Act: -0.0000

Data Index: 37123 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.6546. Min Act: -0.0000

Data Index: 1028523 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.6719. Min Act: -0.0000

Data Index: 158668 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.5875. Min Act: -0.0000

Data Index: 420620 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.4368. Min Act: -0.0000

Data Index: 1122775 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.0661. Min Act: -0.0000

Data Index: 902869 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.4022. Min Act: -0.0000

Data Index: 856848 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.8122. Min Act: -0.0000

Data Index: 574273 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.4294. Min Act: -0.0000

Data Index: 422961 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 6.3773. Min Range: -6.3773

Max Act: 4.4276. Min Act: -0.0000

Data Index: 1241797 (C4 (Web Text))

Max Activating Token Index: 874