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

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

Neuron 2492 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5803. Min Act: -0.0000

Data Index: 951923 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5536. Min Act: -0.0000

Data Index: 676663 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5410. Min Act: -0.0000

Data Index: 831406 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1040643 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5267. Min Act: -0.0000

Data Index: 560023 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5246. Min Act: -0.0000

Data Index: 187953 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5257. Min Act: -0.0000

Data Index: 568778 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1280577 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4801. Min Act: -0.0000

Data Index: 350100 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1210943 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1249620 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4978. Min Act: -0.0000

Data Index: 43908 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4923. Min Act: -0.0000

Data Index: 415904 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4861. Min Act: -0.0000

Data Index: 519162 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4862. Min Act: -0.0000

Data Index: 550409 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4850. Min Act: -0.0000

Data Index: 226725 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4836. Min Act: -0.0000

Data Index: 259067 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4674. Min Act: -0.0000

Data Index: 599010 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4771. Min Act: -0.0000

Data Index: 820558 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.5803. Min Range: -0.5803

Max Act: 0.4600. Min Act: 0.0000

Data Index: 942404 (C4 (Web Text))

Max Activating Token Index: 878