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

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

Neuron 4718 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.1597. Min Act: -0.0002

Data Index: 1296756 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.0615. Min Act: -0.0002

Data Index: 767445 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9422. Min Act: -0.0001

Data Index: 170300 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8675. Min Act: -0.0002

Data Index: 299010 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8738. Min Act: -0.0002

Data Index: 492163 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8372. Min Act: -0.0002

Data Index: 36946 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7846. Min Act: -0.0002

Data Index: 687130 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7705. Min Act: -0.0002

Data Index: 693977 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7942. Min Act: -0.0002

Data Index: 1048817 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7881. Min Act: -0.0002

Data Index: 1289901 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7838. Min Act: -0.0002

Data Index: 1239081 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7526. Min Act: -0.0002

Data Index: 1347577 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7375. Min Act: -0.0002

Data Index: 34876 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7355. Min Act: -0.0002

Data Index: 1126558 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7302. Min Act: -0.0002

Data Index: 1337860 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7517. Min Act: -0.0002

Data Index: 123456 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7300. Min Act: -0.0002

Data Index: 826155 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7482. Min Act: -0.0002

Data Index: 1239093 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7207. Min Act: -0.0002

Data Index: 509557 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7107. Min Act: -0.0002

Data Index: 516223 (C4 (Web Text))

Max Activating Token Index: 31