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

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

Neuron 4637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1547914 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1496149 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1003005 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1531163 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1590241 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1438067 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1380147 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1563993 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1282574 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1487381 (Python Code)

Max Activating Token Index: 243

Text #10

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1031964 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6189. Min Act: -0.0000

Data Index: 838990 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1485763 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5718. Min Act: -0.0000

Data Index: 333705 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1377375 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1037232 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1607240 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1422413 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5792. Min Act: -0.0000

Data Index: 607951 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1643630 (Python Code)

Max Activating Token Index: 519