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

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

Neuron 389 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: 0.1919. Min Range: -0.1919

Max Act: 0.1892. Min Act: -0.0001

Data Index: 101228 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0001

Data Index: 831326 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1863. Min Act: -0.0001

Data Index: 517279 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1853. Min Act: -0.0001

Data Index: 747099 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1833. Min Act: -0.0001

Data Index: 935894 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1208163 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1803. Min Act: -0.0001

Data Index: 863402 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1790. Min Act: -0.0001

Data Index: 817477 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1705. Min Act: -0.0001

Data Index: 125469 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1744. Min Act: -0.0001

Data Index: 397151 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1638. Min Act: -0.0001

Data Index: 892088 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1626. Min Act: -0.0001

Data Index: 883283 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1771. Min Act: -0.0001

Data Index: 753202 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1295851 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1582. Min Act: -0.0001

Data Index: 220117 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1244332 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1558. Min Act: -0.0001

Data Index: 304856 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1867. Min Act: -0.0001

Data Index: 243825 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1786. Min Act: -0.0001

Data Index: 685598 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1588. Min Act: -0.0001

Data Index: 240700 (C4 (Web Text))

Max Activating Token Index: 413