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

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

Neuron 5537 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1348410 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.6267. Min Act: -0.0000

Data Index: 699126 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.5322. Min Act: -0.0000

Data Index: 76714 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.5765. Min Act: -0.0000

Data Index: 383919 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.4156. Min Act: -0.0000

Data Index: 159005 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1136745 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.4122. Min Act: -0.0000

Data Index: 24528 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.2505. Min Act: -0.0000

Data Index: 390991 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.1223. Min Act: -0.0000

Data Index: 109268 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.1047. Min Act: -0.0000

Data Index: 75978 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1108508 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.1376. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1077687 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.6267. Min Range: -1.6267

Max Act: 1.0863. Min Act: -0.0000

Data Index: 621330 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1292949 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.9762. Min Act: -0.0000

Data Index: 872839 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.9209. Min Act: -0.0000

Data Index: 970446 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1261441 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1601911 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 1.6267. Min Range: -1.6267

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1419013 (Python Code)

Max Activating Token Index: 24