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

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

Neuron 471 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0003

Data Index: 217895 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0930. Min Act: -0.0003

Data Index: 151946 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1042196 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1011377 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1307704 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1231529 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0711. Min Act: -0.0003

Data Index: 177190 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1174284 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0728. Min Act: -0.0003

Data Index: 652860 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1289018 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0748. Min Act: -0.0003

Data Index: 493797 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0717. Min Act: -0.0003

Data Index: 636955 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0692. Min Act: -0.0003

Data Index: 52979 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0772. Min Act: -0.0003

Data Index: 783752 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0739. Min Act: -0.0003

Data Index: 534271 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1319419 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0706. Min Act: -0.0003

Data Index: 615479 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1210019 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1048242 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0703. Min Act: -0.0003

Data Index: 471392 (C4 (Web Text))

Max Activating Token Index: 342