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

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

Neuron 3160 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: 0.8741. Min Range: -0.8741

Max Act: 0.8741. Min Act: -0.0000

Data Index: 649304 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.8106. Min Act: -0.0001

Data Index: 917549 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6668. Min Act: -0.0000

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6993. Min Act: -0.0000

Data Index: 447765 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6707. Min Act: -0.0000

Data Index: 876435 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6199. Min Act: -0.0001

Data Index: 786079 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6181. Min Act: -0.0000

Data Index: 400558 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1203754 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6436. Min Act: -0.0001

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6236. Min Act: -0.0000

Data Index: 498048 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5920. Min Act: -0.0000

Data Index: 156360 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6279. Min Act: -0.0000

Data Index: 914400 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5350. Min Act: -0.0000

Data Index: 882163 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5609. Min Act: -0.0000

Data Index: 770901 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1569313 (Python Code)

Max Activating Token Index: 707

Text #15

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5581. Min Act: -0.0001

Data Index: 573767 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5071. Min Act: -0.0000

Data Index: 339991 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5139. Min Act: -0.0000

Data Index: 911536 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1070226 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1649249 (Python Code)

Max Activating Token Index: 200