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

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

Neuron 1934 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9894. Min Act: -0.0000

Data Index: 458105 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.0489. Min Range: -1.0489

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1481480 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1393293 (Python Code)

Max Activating Token Index: 245

Text #3

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8681. Min Act: -0.0000

Data Index: 443041 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1511631 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7747. Min Act: -0.0000

Data Index: 66201 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1302292 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1341853 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8050. Min Act: -0.0000

Data Index: 395281 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7844. Min Act: -0.0000

Data Index: 806855 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1540627 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7443. Min Act: -0.0000

Data Index: 686734 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1625625 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7642. Min Act: 0.0000

Data Index: 1547135 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7495. Min Act: -0.0000

Data Index: 319079 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1412255 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1153654 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7282. Min Act: -0.0000

Data Index: 22053 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7047. Min Act: -0.0000

Data Index: 934555 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1536235 (Python Code)

Max Activating Token Index: 745