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

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

Neuron 1850 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.7244. Min Act: -0.0001

Data Index: 1352065 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.7000. Min Act: -0.0001

Data Index: 111853 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.7015. Min Act: -0.0001

Data Index: 191349 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1199058 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1022837 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1161629 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5754. Min Act: -0.0001

Data Index: 843018 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6300. Min Act: -0.0001

Data Index: 618716 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5967. Min Act: -0.0001

Data Index: 1117895 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6194. Min Act: -0.0001

Data Index: 619064 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6148. Min Act: -0.0001

Data Index: 768806 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5251. Min Act: -0.0001

Data Index: 228130 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5816. Min Act: -0.0001

Data Index: 756598 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5799. Min Act: -0.0001

Data Index: 1303611 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5584. Min Act: -0.0001

Data Index: 542927 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5763. Min Act: -0.0001

Data Index: 847669 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5924. Min Act: -0.0001

Data Index: 255058 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1301183 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5553. Min Act: -0.0001

Data Index: 1050994 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5508. Min Act: -0.0001

Data Index: 782124 (C4 (Web Text))

Max Activating Token Index: 11