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

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

Neuron 927 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: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1482720 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1559399 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1460133 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1544437 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1445146 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1454406 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1521281 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1612978 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1550441 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1529936 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1613629 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1365220 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1611302 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1507313 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1432216 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1391638 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1643283 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1386872 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1629641 (Python Code)

Max Activating Token Index: 969

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1386802 (Python Code)

Max Activating Token Index: 547