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

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

Neuron 3586 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.4582. Min Act: -0.0000

Data Index: 609415 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.6594. Min Act: -0.0000

Data Index: 1244971 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.2732. Min Act: -0.0000

Data Index: 800738 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.2660. Min Act: -0.0000

Data Index: 992714 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.2485. Min Act: 0.0000

Data Index: 798530 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0507. Min Act: -0.0000

Data Index: 178124 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.1702. Min Act: -0.0000

Data Index: 479889 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0544. Min Act: -0.0000

Data Index: 746020 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.3644. Min Act: -0.0000

Data Index: 1251127 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1274205 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.1289. Min Act: -0.0000

Data Index: 901713 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0130. Min Act: -0.0000

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9940. Min Act: 0.0000

Data Index: 808499 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.8593. Min Act: -0.0000

Data Index: 199881 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9690. Min Act: -0.0000

Data Index: 858801 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.8389. Min Act: -0.0000

Data Index: 235882 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9388. Min Act: -0.0000

Data Index: 1163478 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0324. Min Act: -0.0000

Data Index: 1180792 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1160027 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9160. Min Act: 0.0000

Data Index: 529939 (C4 (Web Text))

Max Activating Token Index: 164