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

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

Neuron 2719 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.6010. Min Act: -0.0001

Data Index: 395847 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5372. Min Act: -0.0001

Data Index: 865044 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5025. Min Act: -0.0001

Data Index: 1149735 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5320. Min Act: -0.0001

Data Index: 788521 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4754. Min Act: -0.0001

Data Index: 111800 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1003227 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4335. Min Act: -0.0001

Data Index: 1199605 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4133. Min Act: -0.0001

Data Index: 426397 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4280. Min Act: -0.0001

Data Index: 567729 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1052940 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4055. Min Act: -0.0001

Data Index: 587105 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4058. Min Act: -0.0001

Data Index: 220668 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4040. Min Act: -0.0001

Data Index: 470184 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1177710 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4119. Min Act: -0.0001

Data Index: 1155012 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.3805. Min Act: -0.0001

Data Index: 286272 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4087. Min Act: -0.0001

Data Index: 84192 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4009. Min Act: -0.0001

Data Index: 184276 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4131. Min Act: -0.0001

Data Index: 610311 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.3772. Min Act: -0.0001

Data Index: 852806 (C4 (Web Text))

Max Activating Token Index: 460