Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3336 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.2681. Min Act: -0.0001

Data Index: 412683 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0470. Min Act: -0.0001

Data Index: 607506 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0746. Min Act: -0.0001

Data Index: 379026 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0678. Min Act: -0.0001

Data Index: 692226 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.1061. Min Act: -0.0000

Data Index: 522343 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1138884 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.1087. Min Act: -0.0001

Data Index: 665614 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.1012. Min Act: -0.0001

Data Index: 889804 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.1412. Min Act: -0.0001

Data Index: 578974 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0997. Min Act: -0.0001

Data Index: 858554 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0098. Min Act: -0.0001

Data Index: 589557 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9196. Min Act: -0.0001

Data Index: 868821 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9437. Min Act: -0.0001

Data Index: 275851 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9929. Min Act: -0.0001

Data Index: 998541 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0235. Min Act: -0.0001

Data Index: 1022242 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9478. Min Act: -0.0001

Data Index: 115436 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9792. Min Act: -0.0001

Data Index: 294779 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.2681. Min Range: -1.2681

Max Act: 1.0059. Min Act: -0.0001

Data Index: 1250193 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.9646. Min Act: -0.0000

Data Index: 590623 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.2681. Min Range: -1.2681

Max Act: 0.8869. Min Act: -0.0001

Data Index: 437313 (C4 (Web Text))

Max Activating Token Index: 711