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

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

Neuron 3170 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.6561. Min Act: -0.0003

Data Index: 1372494 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5754. Min Act: -0.0003

Data Index: 1377662 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.6035. Min Act: -0.0003

Data Index: 1554495 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5322. Min Act: -0.0003

Data Index: 1424439 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5111. Min Act: -0.0003

Data Index: 1386410 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5349. Min Act: -0.0003

Data Index: 1507129 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5216. Min Act: -0.0003

Data Index: 1592756 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4925. Min Act: -0.0003

Data Index: 1487808 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4804. Min Act: -0.0002

Data Index: 1479350 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4696. Min Act: -0.0002

Data Index: 1448231 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4411. Min Act: -0.0003

Data Index: 1641273 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4434. Min Act: -0.0003

Data Index: 1452927 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4531. Min Act: -0.0002

Data Index: 1547631 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4487. Min Act: -0.0003

Data Index: 1523279 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4320. Min Act: -0.0003

Data Index: 1448986 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4455. Min Act: -0.0003

Data Index: 1452721 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4426. Min Act: -0.0002

Data Index: 1569005 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4410. Min Act: -0.0003

Data Index: 1547762 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4258. Min Act: -0.0002

Data Index: 1574857 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4374. Min Act: -0.0003

Data Index: 1624244 (Python Code)

Max Activating Token Index: 77