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

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

Neuron 3947 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.9238. Min Act: -0.0000

Data Index: 1465017 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1630876 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1577426 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1568620 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1605807 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1580456 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1457184 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1503998 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1446534 (Python Code)

Max Activating Token Index: 840

Text #9

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1561440 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1471377 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1523231 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1548966 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1455776 (Python Code)

Max Activating Token Index: 922

Text #14

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1477802 (Python Code)

Max Activating Token Index: 80

Text #15

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1501288 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1546452 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4889. Min Act: -0.0000

Data Index: 1453975 (Python Code)

Max Activating Token Index: 722

Text #18

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1457178 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.9238. Min Range: -1.9238

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1430964 (Python Code)

Max Activating Token Index: 169