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

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

Neuron 5044 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: 0.7995. Min Range: -0.7995

Max Act: 0.7995. Min Act: -0.0000

Data Index: 736400 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.7474. Min Act: -0.0001

Data Index: 845726 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.7057. Min Act: -0.0001

Data Index: 810097 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6767. Min Act: -0.0001

Data Index: 1301977 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6848. Min Act: -0.0001

Data Index: 1274678 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6942. Min Act: -0.0001

Data Index: 528859 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6586. Min Act: -0.0001

Data Index: 550404 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6281. Min Act: -0.0001

Data Index: 753127 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1268081 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1328699 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6343. Min Act: -0.0001

Data Index: 613653 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.5893. Min Act: -0.0001

Data Index: 1270608 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6467. Min Act: -0.0001

Data Index: 735970 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6574. Min Act: -0.0001

Data Index: 463689 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1024643 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6090. Min Act: -0.0000

Data Index: 348714 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1199085 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.5779. Min Act: -0.0001

Data Index: 983352 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.6172. Min Act: -0.0001

Data Index: 556860 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.7995. Min Range: -0.7995

Max Act: 0.5481. Min Act: -0.0001

Data Index: 705399 (C4 (Web Text))

Max Activating Token Index: 152