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

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

Neuron 2750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6973. Min Act: -0.0000

Data Index: 243592 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6037. Min Act: -0.0000

Data Index: 634272 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6006. Min Act: -0.0000

Data Index: 367796 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1321220 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6387. Min Act: -0.0000

Data Index: 821313 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5963. Min Act: -0.0000

Data Index: 706256 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6194. Min Act: -0.0000

Data Index: 512628 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1078391 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5482. Min Act: -0.0000

Data Index: 927677 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5333. Min Act: -0.0000

Data Index: 849042 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5501. Min Act: -0.0000

Data Index: 740144 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1085767 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5628. Min Act: -0.0000

Data Index: 273742 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1068534 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1045636 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1016843 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5166. Min Act: -0.0000

Data Index: 579257 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1303298 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5242. Min Act: -0.0000

Data Index: 631200 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.4656. Min Act: -0.0000

Data Index: 534295 (C4 (Web Text))

Max Activating Token Index: 757