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

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

Neuron 316 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.2158. Min Act: -0.0000

Data Index: 314180 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1043595 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1181773 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1315464 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1092854 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1894. Min Act: -0.0000

Data Index: 338320 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1825. Min Act: -0.0000

Data Index: 314936 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1222428 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1126660 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1669. Min Act: -0.0000

Data Index: 399487 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1125453 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1703. Min Act: -0.0000

Data Index: 581107 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1596. Min Act: -0.0000

Data Index: 755901 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1369426 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1746. Min Act: -0.0000

Data Index: 825154 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1605. Min Act: -0.0000

Data Index: 142253 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1554. Min Act: -0.0000

Data Index: 758446 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1286839 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1589. Min Act: -0.0000

Data Index: 46481 (C4 (Web Text))

Max Activating Token Index: 59