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

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

Neuron 4005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0000

Data Index: 137110 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1253. Min Act: -0.0000

Data Index: 424860 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1194. Min Act: -0.0000

Data Index: 629403 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1205. Min Act: -0.0000

Data Index: 912314 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1133. Min Act: -0.0001

Data Index: 218426 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1014. Min Act: -0.0000

Data Index: 245548 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0997. Min Act: -0.0001

Data Index: 193902 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1170309 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1058. Min Act: -0.0001

Data Index: 642737 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0962. Min Act: -0.0001

Data Index: 137014 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0985. Min Act: -0.0000

Data Index: 770244 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1151713 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1141435 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0999. Min Act: -0.0001

Data Index: 521468 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0889. Min Act: -0.0001

Data Index: 449810 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0918. Min Act: -0.0000

Data Index: 620702 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1133461 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0873. Min Act: -0.0001

Data Index: 246502 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0902. Min Act: -0.0000

Data Index: 710316 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1132047 (C4 (Web Text))

Max Activating Token Index: 16