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

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

Neuron 3966 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: 1.6210. Min Range: -1.6210

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1496915 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1437108 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1514368 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.4533. Min Act: -0.0000

Data Index: 715017 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1499048 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.4914. Min Act: -0.0000

Data Index: 111900 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1611268 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1494285 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1379484 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1361336 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1651065 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2795. Min Act: -0.0000

Data Index: 929776 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1389049 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1640517 (Python Code)

Max Activating Token Index: 897

Text #14

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1434706 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3951. Min Act: -0.0000

Data Index: 1542452 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3340. Min Act: -0.0000

Data Index: 284070 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1632376 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3972. Min Act: -0.0000

Data Index: 191636 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1540033 (Python Code)

Max Activating Token Index: 331