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

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

Neuron 4800 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: 0.3522. Min Range: -0.3522

Max Act: 0.3401. Min Act: -0.0000

Data Index: 369101 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3102. Min Act: -0.0000

Data Index: 149745 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3522. Min Act: -0.0000

Data Index: 156898 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1115212 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3209. Min Act: -0.0000

Data Index: 268614 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2999. Min Act: -0.0000

Data Index: 18427 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2175. Min Act: -0.0000

Data Index: 617930 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2225. Min Act: -0.0000

Data Index: 304607 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1016067 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2125. Min Act: -0.0000

Data Index: 40687 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1079100 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.1993. Min Act: -0.0000

Data Index: 553887 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.1955. Min Act: -0.0000

Data Index: 259617 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2030. Min Act: -0.0000

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1196736 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1165529 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2087. Min Act: -0.0000

Data Index: 989227 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2100. Min Act: -0.0001

Data Index: 273286 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.1913. Min Act: -0.0000

Data Index: 542823 (C4 (Web Text))

Max Activating Token Index: 799