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

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

Neuron 3235 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0000

Data Index: 493815 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1728. Min Act: -0.0000

Data Index: 406321 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1421. Min Act: 0.0000

Data Index: 924942 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1421. Min Act: -0.0000

Data Index: 192988 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1349660 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1158863 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1265. Min Act: -0.0000

Data Index: 772704 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1031411 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1239. Min Act: -0.0000

Data Index: 415073 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1187. Min Act: -0.0000

Data Index: 608640 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1182347 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1213. Min Act: -0.0000

Data Index: 842602 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1221. Min Act: -0.0000

Data Index: 862791 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1149. Min Act: -0.0000

Data Index: 389529 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1144. Min Act: -0.0000

Data Index: 19422 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1116. Min Act: -0.0000

Data Index: 616167 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1155. Min Act: 0.0000

Data Index: 349363 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1097. Min Act: -0.0000

Data Index: 342862 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1127299 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1062. Min Act: -0.0000

Data Index: 991280 (C4 (Web Text))

Max Activating Token Index: 412