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

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

Neuron 1759 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: 0.7052. Min Range: -0.7052

Max Act: 0.6603. Min Act: -0.0001

Data Index: 359410 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.7052. Min Act: -0.0001

Data Index: 494754 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1023857 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.6460. Min Act: -0.0001

Data Index: 326772 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5887. Min Act: -0.0001

Data Index: 904459 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5721. Min Act: -0.0000

Data Index: 486277 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1256497 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1157424 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.6047. Min Act: -0.0000

Data Index: 422361 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5643. Min Act: -0.0000

Data Index: 651976 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5819. Min Act: -0.0001

Data Index: 117987 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5811. Min Act: -0.0001

Data Index: 535897 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1008727 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5762. Min Act: -0.0001

Data Index: 1080831 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5080. Min Act: -0.0001

Data Index: 800507 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5803. Min Act: -0.0000

Data Index: 530504 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5843. Min Act: -0.0000

Data Index: 104480 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5627. Min Act: -0.0001

Data Index: 305440 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1195744 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.7052. Min Range: -0.7052

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1189808 (C4 (Web Text))

Max Activating Token Index: 550