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

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

Neuron 3500 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0695. Min Act: -0.0002

Data Index: 1129638 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0486. Min Act: -0.0002

Data Index: 862447 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0369. Min Act: -0.0002

Data Index: 49233 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0207. Min Act: -0.0002

Data Index: 68159 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0200. Min Act: -0.0002

Data Index: 204845 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0187. Min Act: -0.0003

Data Index: 703828 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9982. Min Act: -0.0002

Data Index: 682136 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9949. Min Act: -0.0002

Data Index: 478229 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9899. Min Act: -0.0002

Data Index: 1323104 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0168. Min Act: -0.0002

Data Index: 681654 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9987. Min Act: -0.0002

Data Index: 1168983 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9856. Min Act: -0.0002

Data Index: 838739 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9780. Min Act: -0.0002

Data Index: 1242326 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9768. Min Act: -0.0002

Data Index: 1194864 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9675. Min Act: -0.0002

Data Index: 143431 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9867. Min Act: -0.0002

Data Index: 791296 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9833. Min Act: -0.0002

Data Index: 492388 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9689. Min Act: -0.0002

Data Index: 721640 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9739. Min Act: -0.0003

Data Index: 318111 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9748. Min Act: -0.0002

Data Index: 939275 (C4 (Web Text))

Max Activating Token Index: 79