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

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

Neuron 1506 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.8945. Min Act: -0.0002

Data Index: 1340190 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.9388. Min Act: -0.0002

Data Index: 92305 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.8694. Min Act: -0.0002

Data Index: 947231 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.7326. Min Act: -0.0002

Data Index: 187122 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.7822. Min Act: -0.0002

Data Index: 533868 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.7422. Min Act: -0.0002

Data Index: 933526 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.7206. Min Act: -0.0002

Data Index: 598007 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6704. Min Act: -0.0002

Data Index: 679815 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6719. Min Act: -0.0002

Data Index: 667536 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6745. Min Act: -0.0002

Data Index: 939110 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6682. Min Act: -0.0002

Data Index: 1169829 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6248. Min Act: -0.0002

Data Index: 110851 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6270. Min Act: -0.0002

Data Index: 437653 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5604. Min Act: -0.0002

Data Index: 1205758 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5776. Min Act: -0.0002

Data Index: 790480 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6108. Min Act: -0.0002

Data Index: 243967 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5713. Min Act: -0.0002

Data Index: 1324181 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5641. Min Act: -0.0002

Data Index: 908426 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5450. Min Act: -0.0002

Data Index: 145105 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5725. Min Act: -0.0002

Data Index: 1094485 (C4 (Web Text))

Max Activating Token Index: 521