Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.4689. Min Act: -0.0000

Data Index: 1183780 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 4.4689. Min Range: -4.4689

Max Act: 3.7676. Min Act: -0.0000

Data Index: 379572 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.9180. Min Act: -0.0000

Data Index: 820585 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1250414 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.4278. Min Act: -0.0000

Data Index: 548286 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.2849. Min Act: -0.0000

Data Index: 47278 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.2599. Min Act: -0.0000

Data Index: 750666 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1308393 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.0931. Min Act: -0.0000

Data Index: 845448 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9717. Min Act: -0.0000

Data Index: 882739 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9428. Min Act: -0.0000

Data Index: 1101722 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.0335. Min Act: -0.0000

Data Index: 157568 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9836. Min Act: -0.0000

Data Index: 595889 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9861. Min Act: -0.0000

Data Index: 450620 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9344. Min Act: -0.0000

Data Index: 449415 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.9254. Min Act: -0.0000

Data Index: 1312651 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.8659. Min Act: -0.0000

Data Index: 907786 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 4.4689. Min Range: -4.4689

Max Act: 2.0696. Min Act: -0.0000

Data Index: 1003103 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.8167. Min Act: -0.0000

Data Index: 29591 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 4.4689. Min Range: -4.4689

Max Act: 1.8736. Min Act: -0.0000

Data Index: 962119 (C4 (Web Text))

Max Activating Token Index: 950