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

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

Neuron 1460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.4232. Min Act: -0.0000

Data Index: 154819 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1101180 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3665. Min Act: -0.0000

Data Index: 63415 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3699. Min Act: -0.0000

Data Index: 96153 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3896. Min Act: -0.0000

Data Index: 460477 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3723. Min Act: -0.0000

Data Index: 383087 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3748. Min Act: -0.0000

Data Index: 850337 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3579. Min Act: -0.0000

Data Index: 58737 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1139038 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3459. Min Act: -0.0000

Data Index: 977119 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1106068 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1018414 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3379. Min Act: -0.0000

Data Index: 164062 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1168815 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3415. Min Act: -0.0000

Data Index: 253010 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1045826 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3229. Min Act: -0.0000

Data Index: 275072 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1038110 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3266. Min Act: -0.0000

Data Index: 151373 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1233284 (C4 (Web Text))

Max Activating Token Index: 565