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

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

Neuron 5464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3295. Min Range: -4.3295

Max Act: 4.3295. Min Act: -0.0000

Data Index: 64287 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 4.3295. Min Range: -4.3295

Max Act: 4.1109. Min Act: -0.0000

Data Index: 1140626 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 4.3295. Min Range: -4.3295

Max Act: 4.0334. Min Act: -0.0000

Data Index: 622768 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.6289. Min Act: -0.0000

Data Index: 148176 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.8977. Min Act: -0.0000

Data Index: 259161 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 4.3295. Min Range: -4.3295

Max Act: 4.0829. Min Act: -0.0000

Data Index: 73591 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.7068. Min Act: -0.0000

Data Index: 290801 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.4700. Min Act: -0.0000

Data Index: 194093 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.8084. Min Act: -0.0000

Data Index: 722881 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.9746. Min Act: -0.0000

Data Index: 303291 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.8020. Min Act: -0.0000

Data Index: 1013660 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.5843. Min Act: -0.0000

Data Index: 360276 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.6467. Min Act: -0.0000

Data Index: 961743 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.5222. Min Act: -0.0000

Data Index: 486214 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.4955. Min Act: -0.0000

Data Index: 525406 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.7189. Min Act: -0.0000

Data Index: 170223 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.5126. Min Act: -0.0000

Data Index: 328043 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.3267. Min Act: -0.0000

Data Index: 922796 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.3295. Min Range: -4.3295

Max Act: 3.0182. Min Act: -0.0000

Data Index: 1123682 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 4.3295. Min Range: -4.3295

Max Act: 2.9832. Min Act: -0.0000

Data Index: 888867 (C4 (Web Text))

Max Activating Token Index: 326