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

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

Neuron 4545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.6740. Min Act: -0.0000

Data Index: 144144 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.6347. Min Act: -0.0000

Data Index: 322828 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.5229. Min Act: -0.0000

Data Index: 442564 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.3963. Min Act: -0.0000

Data Index: 596355 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1736. Min Act: -0.0000

Data Index: 728022 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1948. Min Act: -0.0000

Data Index: 1094976 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1847. Min Act: -0.0000

Data Index: 116123 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1244189 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1350. Min Act: -0.0000

Data Index: 782471 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.2418. Min Act: -0.0000

Data Index: 573087 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.0986. Min Act: -0.0000

Data Index: 462761 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9847. Min Act: -0.0000

Data Index: 1147630 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1981. Min Act: -0.0000

Data Index: 883527 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9770. Min Act: -0.0000

Data Index: 1060156 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9603. Min Act: -0.0000

Data Index: 932481 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9297. Min Act: -0.0000

Data Index: 320009 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.0119. Min Act: -0.0000

Data Index: 542480 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 2.6740. Min Range: -2.6740

Max Act: 2.1194. Min Act: -0.0000

Data Index: 740845 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9752. Min Act: -0.0000

Data Index: 1085560 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 2.6740. Min Range: -2.6740

Max Act: 1.9663. Min Act: -0.0000

Data Index: 665913 (C4 (Web Text))

Max Activating Token Index: 663