Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 777 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1251848 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1017546 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1348675 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4192. Min Act: -0.0001

Data Index: 698614 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4254. Min Act: -0.0001

Data Index: 785902 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4061. Min Act: -0.0001

Data Index: 1264401 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.4070. Min Act: -0.0001

Data Index: 717429 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1343728 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3928. Min Act: -0.0001

Data Index: 1145526 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3896. Min Act: -0.0001

Data Index: 393445 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3897. Min Act: -0.0001

Data Index: 316737 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3885. Min Act: -0.0001

Data Index: 370972 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3715. Min Act: -0.0001

Data Index: 94491 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1087103 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3572. Min Act: -0.0001

Data Index: 1010203 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3769. Min Act: -0.0001

Data Index: 250840 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3726. Min Act: -0.0001

Data Index: 604434 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1151129 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3783. Min Act: -0.0001

Data Index: 664486 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.4579. Min Range: -0.4579

Max Act: 0.3720. Min Act: -0.0001

Data Index: 496305 (C4 (Web Text))

Max Activating Token Index: 900