Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.6854. Min Act: -0.0000

Data Index: 835839 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.7709. Min Act: -0.0000

Data Index: 287690 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1323613 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.6812. Min Act: -0.0000

Data Index: 873546 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3856. Min Act: -0.0000

Data Index: 895373 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4443. Min Act: -0.0000

Data Index: 107838 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1047644 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1294000 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4425. Min Act: -0.0000

Data Index: 906265 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4159. Min Act: -0.0000

Data Index: 111156 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4070. Min Act: -0.0000

Data Index: 912837 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.1678. Min Act: -0.0000

Data Index: 159861 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2071. Min Act: -0.0000

Data Index: 239399 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2677. Min Act: -0.0000

Data Index: 36105 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.1892. Min Act: -0.0000

Data Index: 999254 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1287933 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1150025 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2296. Min Act: -0.0000

Data Index: 959039 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2267. Min Act: -0.0000

Data Index: 880258 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.1390. Min Act: -0.0000

Data Index: 57292 (C4 (Web Text))

Max Activating Token Index: 186