Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.1001. Min Act: -0.0002

Data Index: 140887 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0299. Min Act: -0.0002

Data Index: 1006083 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0549. Min Act: -0.0001

Data Index: 343860 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0025. Min Act: -0.0002

Data Index: 436844 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0352. Min Act: -0.0001

Data Index: 138760 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9753. Min Act: -0.0001

Data Index: 1140743 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0004. Min Act: -0.0002

Data Index: 137485 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9811. Min Act: -0.0002

Data Index: 41083 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9519. Min Act: -0.0002

Data Index: 91990 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0023. Min Act: -0.0002

Data Index: 11456 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0125. Min Act: -0.0001

Data Index: 636360 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1190073 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0261. Min Act: -0.0001

Data Index: 978862 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9839. Min Act: -0.0001

Data Index: 891888 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9934. Min Act: -0.0002

Data Index: 410950 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9140. Min Act: -0.0002

Data Index: 1348039 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9995. Min Act: -0.0001

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9029. Min Act: -0.0002

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.1001. Min Range: -1.1001

Max Act: 1.0198. Min Act: -0.0002

Data Index: 431464 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.1001. Min Range: -1.1001

Max Act: 0.9008. Min Act: -0.0002

Data Index: 364536 (C4 (Web Text))

Max Activating Token Index: 695