Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1612 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2180. Min Act: -0.0001

Data Index: 866392 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2048. Min Act: -0.0001

Data Index: 121561 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1915. Min Act: -0.0001

Data Index: 919971 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1219925 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1855. Min Act: -0.0001

Data Index: 294006 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1784. Min Act: -0.0001

Data Index: 752639 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1838. Min Act: -0.0001

Data Index: 687685 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1925. Min Act: -0.0001

Data Index: 519030 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1885. Min Act: -0.0001

Data Index: 575653 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1992. Min Act: -0.0001

Data Index: 748974 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1798. Min Act: -0.0001

Data Index: 313015 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1717. Min Act: -0.0001

Data Index: 429239 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1769. Min Act: -0.0001

Data Index: 683336 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1074240 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1674. Min Act: -0.0001

Data Index: 398268 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1661. Min Act: -0.0001

Data Index: 36307 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1344343 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1747. Min Act: -0.0001

Data Index: 720005 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1629. Min Act: -0.0001

Data Index: 291203 (C4 (Web Text))

Max Activating Token Index: 157