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

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

Neuron 533 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: 2.1734. Min Range: -2.1734

Max Act: 2.1734. Min Act: -0.0000

Data Index: 940199 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.1734. Min Range: -2.1734

Max Act: 2.0440. Min Act: -0.0000

Data Index: 859241 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.1734. Min Range: -2.1734

Max Act: 2.1371. Min Act: -0.0000

Data Index: 2922 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.8983. Min Act: -0.0000

Data Index: 201842 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.7760. Min Act: -0.0000

Data Index: 894794 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.8675. Min Act: -0.0000

Data Index: 536282 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6810. Min Act: -0.0000

Data Index: 133020 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6379. Min Act: -0.0000

Data Index: 238997 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.7213. Min Act: -0.0000

Data Index: 125528 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.7080. Min Act: -0.0000

Data Index: 749626 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6196. Min Act: -0.0000

Data Index: 759922 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.8714. Min Act: -0.0000

Data Index: 538650 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6688. Min Act: -0.0000

Data Index: 985158 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6530. Min Act: -0.0000

Data Index: 604357 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6365. Min Act: -0.0000

Data Index: 1174117 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.5997. Min Act: -0.0000

Data Index: 54246 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.6081. Min Act: -0.0000

Data Index: 1257203 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.4424. Min Act: -0.0000

Data Index: 496326 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.5964. Min Act: -0.0000

Data Index: 449432 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.1734. Min Range: -2.1734

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1166345 (C4 (Web Text))

Max Activating Token Index: 42