Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 106 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 534680 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0983. Min Act: -0.0001

Data Index: 757176 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0899. Min Act: -0.0001

Data Index: 68646 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0838. Min Act: -0.0001

Data Index: 534151 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0862. Min Act: -0.0001

Data Index: 351270 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1350239 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0833. Min Act: -0.0001

Data Index: 942155 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1048165 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0792. Min Act: -0.0001

Data Index: 895994 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0815. Min Act: -0.0001

Data Index: 549690 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0783. Min Act: -0.0001

Data Index: 446067 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0774. Min Act: -0.0001

Data Index: 213691 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0754. Min Act: -0.0000

Data Index: 142705 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0790. Min Act: -0.0001

Data Index: 732633 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1031379 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0749. Min Act: -0.0001

Data Index: 853867 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0684. Min Act: -0.0001

Data Index: 413835 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0757. Min Act: -0.0001

Data Index: 340489 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0689. Min Act: -0.0001

Data Index: 234407 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1211518 (C4 (Web Text))

Max Activating Token Index: 502