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

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

Neuron 5957 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1157393 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1049480 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1232065 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0386. Min Act: -0.0000

Data Index: 568370 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1227807 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0023. Min Act: -0.0000

Data Index: 8792 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9327. Min Act: -0.0000

Data Index: 194486 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9574. Min Act: -0.0000

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9761. Min Act: -0.0000

Data Index: 692908 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1034310 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9670. Min Act: -0.0000

Data Index: 547751 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9655. Min Act: -0.0000

Data Index: 77949 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9120. Min Act: -0.0000

Data Index: 454353 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9190. Min Act: -0.0000

Data Index: 132084 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9589. Min Act: -0.0000

Data Index: 658558 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9498. Min Act: -0.0000

Data Index: 448032 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9422. Min Act: -0.0000

Data Index: 424829 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9087. Min Act: -0.0000

Data Index: 495863 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1260767 (C4 (Web Text))

Max Activating Token Index: 985