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

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

Neuron 5209 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: 0.2791. Min Range: -0.2791

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1235700 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1325865 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2461. Min Act: -0.0000

Data Index: 19589 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1326747 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2240. Min Act: -0.0000

Data Index: 423554 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2043. Min Act: -0.0000

Data Index: 350192 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1340347 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1902. Min Act: -0.0000

Data Index: 806229 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1783. Min Act: -0.0000

Data Index: 432095 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1741. Min Act: -0.0000

Data Index: 634384 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1778. Min Act: -0.0000

Data Index: 815963 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1097595 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1710. Min Act: -0.0000

Data Index: 912674 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1790. Min Act: -0.0000

Data Index: 419252 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1617. Min Act: -0.0000

Data Index: 389786 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1689. Min Act: -0.0000

Data Index: 520015 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1689. Min Act: -0.0000

Data Index: 61675 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1578. Min Act: -0.0000

Data Index: 122715 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1591. Min Act: -0.0000

Data Index: 696299 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1503. Min Act: -0.0000

Data Index: 785231 (C4 (Web Text))

Max Activating Token Index: 173