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

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

Neuron 3337 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.1161. Min Act: -0.0001

Data Index: 388861 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0859. Min Act: -0.0001

Data Index: 583364 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.1186. Min Act: -0.0000

Data Index: 523318 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0762. Min Act: -0.0000

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0731. Min Act: -0.0000

Data Index: 876487 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0424. Min Act: -0.0001

Data Index: 39315 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0943. Min Act: -0.0001

Data Index: 342451 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0682. Min Act: -0.0001

Data Index: 272337 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0622. Min Act: -0.0000

Data Index: 147168 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0781. Min Act: -0.0001

Data Index: 1344888 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9978. Min Act: -0.0001

Data Index: 239381 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9975. Min Act: -0.0001

Data Index: 1327807 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0677. Min Act: -0.0000

Data Index: 164326 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0146. Min Act: -0.0001

Data Index: 98024 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0197. Min Act: -0.0000

Data Index: 136901 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9658. Min Act: -0.0001

Data Index: 13870 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9629. Min Act: -0.0000

Data Index: 940966 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9721. Min Act: -0.0001

Data Index: 426682 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9520. Min Act: -0.0001

Data Index: 146546 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1050898 (C4 (Web Text))

Max Activating Token Index: 305