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

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

Neuron 3147 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.6246. Min Act: -0.0001

Data Index: 80346 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1018967 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5960. Min Act: -0.0001

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.6049. Min Act: -0.0000

Data Index: 596418 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5709. Min Act: -0.0001

Data Index: 657512 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5101. Min Act: -0.0001

Data Index: 970700 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1213925 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5884. Min Act: -0.0000

Data Index: 472446 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5391. Min Act: -0.0001

Data Index: 323300 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5174. Min Act: -0.0001

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5021. Min Act: -0.0001

Data Index: 1026006 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.4954. Min Act: -0.0000

Data Index: 407123 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5267. Min Act: -0.0001

Data Index: 1313881 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1144359 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.4923. Min Act: -0.0001

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.4870. Min Act: -0.0000

Data Index: 749102 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5195. Min Act: -0.0000

Data Index: 684005 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.4496. Min Act: -0.0001

Data Index: 873265 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.4858. Min Act: -0.0001

Data Index: 960639 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.6630. Min Range: -0.6630

Max Act: 0.5125. Min Act: -0.0001

Data Index: 395139 (C4 (Web Text))

Max Activating Token Index: 927