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

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

Neuron 1330 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: 1.7063. Min Range: -1.7063

Max Act: 1.7063. Min Act: -0.0000

Data Index: 826459 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.5762. Min Act: -0.0000

Data Index: 171676 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.5442. Min Act: -0.0000

Data Index: 1258132 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4445. Min Act: -0.0000

Data Index: 563434 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4931. Min Act: -0.0000

Data Index: 292430 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1639289 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1653936 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1196122 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1424437 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.5115. Min Act: -0.0000

Data Index: 950928 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1160356 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.3639. Min Act: -0.0000

Data Index: 640913 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4500. Min Act: -0.0000

Data Index: 123957 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.4090. Min Act: -0.0000

Data Index: 515882 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1424722 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.3109. Min Act: -0.0000

Data Index: 773594 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1376167 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1255872 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.1358. Min Act: -0.0000

Data Index: 799552 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.7063. Min Range: -1.7063

Max Act: 1.3303. Min Act: -0.0000

Data Index: 981093 (C4 (Web Text))

Max Activating Token Index: 16