Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.7885. Min Act: -0.0002

Data Index: 520659 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6024. Min Act: -0.0001

Data Index: 726152 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6748. Min Act: -0.0002

Data Index: 1216431 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6260. Min Act: -0.0001

Data Index: 680004 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5828. Min Act: -0.0002

Data Index: 219581 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5998. Min Act: -0.0002

Data Index: 1313497 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5447. Min Act: -0.0002

Data Index: 1206308 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5659. Min Act: -0.0002

Data Index: 149599 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4780. Min Act: -0.0002

Data Index: 87356 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4932. Min Act: -0.0002

Data Index: 830652 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1331493 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4891. Min Act: -0.0002

Data Index: 218755 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4860. Min Act: -0.0001

Data Index: 206185 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5160. Min Act: -0.0002

Data Index: 78109 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4886. Min Act: -0.0002

Data Index: 799960 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4740. Min Act: -0.0002

Data Index: 1351581 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5150. Min Act: -0.0001

Data Index: 327623 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4699. Min Act: -0.0001

Data Index: 234895 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4610. Min Act: -0.0002

Data Index: 1085509 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4486. Min Act: -0.0002

Data Index: 366132 (C4 (Web Text))

Max Activating Token Index: 267