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

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

Neuron 2099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0865. Min Act: -0.0002

Data Index: 259157 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1177492 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0854. Min Act: -0.0002

Data Index: 839193 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1334869 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0750. Min Act: -0.0002

Data Index: 339387 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0742. Min Act: -0.0002

Data Index: 537435 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0800. Min Act: -0.0002

Data Index: 174958 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0828. Min Act: -0.0002

Data Index: 629953 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1180151 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0683. Min Act: -0.0002

Data Index: 693907 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1326698 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0657. Min Act: -0.0002

Data Index: 81165 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0709. Min Act: -0.0002

Data Index: 607688 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0704. Min Act: -0.0002

Data Index: 9553 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0679. Min Act: -0.0002

Data Index: 116875 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0682. Min Act: -0.0002

Data Index: 70060 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0616. Min Act: -0.0002

Data Index: 682377 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0640. Min Act: -0.0002

Data Index: 992674 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0685. Min Act: -0.0002

Data Index: 916503 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0654. Min Act: -0.0002

Data Index: 349560 (C4 (Web Text))

Max Activating Token Index: 98