Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7824. Min Act: -0.0000

Data Index: 510054 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7031. Min Act: -0.0000

Data Index: 465427 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7135. Min Act: -0.0000

Data Index: 550273 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7089. Min Act: -0.0000

Data Index: 366053 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7297. Min Act: -0.0000

Data Index: 577717 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6365. Min Act: -0.0001

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6411. Min Act: -0.0000

Data Index: 298549 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6124. Min Act: -0.0000

Data Index: 372777 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6045. Min Act: -0.0000

Data Index: 982580 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6037. Min Act: -0.0000

Data Index: 601887 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5969. Min Act: -0.0001

Data Index: 926215 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5464. Min Act: -0.0000

Data Index: 535096 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6174. Min Act: -0.0001

Data Index: 352338 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5751. Min Act: -0.0000

Data Index: 755436 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5798. Min Act: -0.0001

Data Index: 436369 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5603. Min Act: -0.0000

Data Index: 23850 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5420. Min Act: -0.0001

Data Index: 583048 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5704. Min Act: -0.0000

Data Index: 263721 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5147. Min Act: -0.0001

Data Index: 1167536 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1068829 (C4 (Web Text))

Max Activating Token Index: 487