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

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

Neuron 3532 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: 0.5781. Min Range: -0.5781

Max Act: 0.5781. Min Act: -0.0001

Data Index: 1264953 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1196787 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.5384. Min Act: -0.0002

Data Index: 1347217 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.5076. Min Act: -0.0001

Data Index: 388433 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.5217. Min Act: -0.0002

Data Index: 952348 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.5092. Min Act: -0.0002

Data Index: 201281 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4793. Min Act: -0.0001

Data Index: 152096 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4759. Min Act: -0.0001

Data Index: 275409 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4750. Min Act: -0.0002

Data Index: 1176626 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4996. Min Act: -0.0001

Data Index: 478260 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4833. Min Act: -0.0001

Data Index: 811592 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4658. Min Act: -0.0001

Data Index: 4529 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4807. Min Act: -0.0002

Data Index: 950241 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4528. Min Act: -0.0001

Data Index: 269796 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1089247 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4589. Min Act: -0.0001

Data Index: 1230488 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4276. Min Act: -0.0001

Data Index: 91525 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4448. Min Act: -0.0001

Data Index: 158482 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4044. Min Act: -0.0002

Data Index: 487913 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.5781. Min Range: -0.5781

Max Act: 0.4051. Min Act: -0.0001

Data Index: 494199 (C4 (Web Text))

Max Activating Token Index: 695