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

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

Neuron 460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5904. Min Act: -0.0000

Data Index: 287947 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1253646 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5595. Min Act: -0.0000

Data Index: 460005 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.6097. Min Act: -0.0000

Data Index: 358163 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5876. Min Act: -0.0000

Data Index: 497264 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5776. Min Act: -0.0000

Data Index: 125924 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5851. Min Act: -0.0000

Data Index: 443894 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.6001. Min Act: -0.0000

Data Index: 33089 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5236. Min Act: -0.0000

Data Index: 984097 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5110. Min Act: -0.0000

Data Index: 815193 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5449. Min Act: -0.0000

Data Index: 885768 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5491. Min Act: -0.0000

Data Index: 427252 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1219558 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1271459 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5321. Min Act: -0.0000

Data Index: 961469 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5168. Min Act: -0.0000

Data Index: 467207 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5379. Min Act: -0.0000

Data Index: 586259 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5020. Min Act: -0.0000

Data Index: 950535 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5211. Min Act: -0.0000

Data Index: 400558 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5423. Min Act: -0.0000

Data Index: 769332 (C4 (Web Text))

Max Activating Token Index: 821