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

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

Neuron 35 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.2690. Min Act: 0.0001

Data Index: 311864 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0643. Min Act: 0.0000

Data Index: 494899 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0634. Min Act: 0.0001

Data Index: 573753 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9650. Min Act: -0.0000

Data Index: 562546 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9915. Min Act: 0.0000

Data Index: 1141833 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9302. Min Act: 0.0000

Data Index: 256506 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9487. Min Act: -0.0000

Data Index: 884910 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9188. Min Act: -0.0000

Data Index: 756995 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9200. Min Act: 0.0000

Data Index: 1187176 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8882. Min Act: -0.0000

Data Index: 486011 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9074. Min Act: -0.0000

Data Index: 256855 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1086406 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8399. Min Act: 0.0001

Data Index: 184130 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1137856 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8732. Min Act: 0.0000

Data Index: 1170128 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8431. Min Act: -0.0000

Data Index: 167345 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8379. Min Act: 0.0000

Data Index: 672790 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1213482 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8093. Min Act: 0.0000

Data Index: 169134 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.7780. Min Act: 0.0000

Data Index: 397662 (C4 (Web Text))

Max Activating Token Index: 1009