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

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

Neuron 1805 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1101044 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2587. Min Act: -0.0000

Data Index: 607548 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1121726 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2351. Min Act: -0.0000

Data Index: 496617 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2201. Min Act: -0.0001

Data Index: 259985 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2295. Min Act: -0.0001

Data Index: 876569 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2150. Min Act: -0.0001

Data Index: 85267 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2310. Min Act: -0.0000

Data Index: 497787 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1188558 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2025. Min Act: -0.0000

Data Index: 286455 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1958. Min Act: -0.0000

Data Index: 661932 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2182. Min Act: -0.0001

Data Index: 454891 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1846. Min Act: -0.0001

Data Index: 297654 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2057. Min Act: -0.0001

Data Index: 318577 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2096. Min Act: -0.0001

Data Index: 663172 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1160137 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1990. Min Act: -0.0000

Data Index: 419159 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1237309 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1349590 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1267183 (C4 (Web Text))

Max Activating Token Index: 564