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

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

Neuron 2914 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0817. Min Range: -2.0817

Max Act: 2.0817. Min Act: -0.0000

Data Index: 145956 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 2.0817. Min Range: -2.0817

Max Act: 2.0088. Min Act: -0.0000

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.8619. Min Act: -0.0000

Data Index: 334660 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7866. Min Act: -0.0000

Data Index: 137669 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7661. Min Act: -0.0000

Data Index: 429208 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7207. Min Act: -0.0000

Data Index: 849168 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1124762 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6938. Min Act: -0.0000

Data Index: 259792 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7749. Min Act: -0.0000

Data Index: 164347 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7933. Min Act: -0.0000

Data Index: 1053048 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.7490. Min Act: -0.0000

Data Index: 604058 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6308. Min Act: -0.0000

Data Index: 480635 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6383. Min Act: -0.0000

Data Index: 580961 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6242. Min Act: 0.0002

Data Index: 725214 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6515. Min Act: 0.0002

Data Index: 1528591 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6712. Min Act: -0.0000

Data Index: 291477 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1133271 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6265. Min Act: 0.0000

Data Index: 297206 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6075. Min Act: -0.0000

Data Index: 288884 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.0817. Min Range: -2.0817

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1348832 (C4 (Web Text))

Max Activating Token Index: 713