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

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

Neuron 1404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.5858. Min Act: -0.0000

Data Index: 104238 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.3537. Min Act: -0.0000

Data Index: 380468 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.2589. Min Act: -0.0000

Data Index: 188683 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.2331. Min Act: -0.0000

Data Index: 573152 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.1782. Min Act: -0.0000

Data Index: 275353 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.1202. Min Act: -0.0000

Data Index: 428421 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1256186 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.1820. Min Act: -0.0000

Data Index: 236844 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.1069. Min Act: -0.0000

Data Index: 880975 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1344438 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0828. Min Act: -0.0000

Data Index: 136034 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0199. Min Act: -0.0000

Data Index: 76599 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0925. Min Act: -0.0000

Data Index: 42314 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0788. Min Act: -0.0000

Data Index: 452784 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1318938 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.5858. Min Range: -1.5858

Max Act: 1.0066. Min Act: -0.0000

Data Index: 291179 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.5858. Min Range: -1.5858

Max Act: 0.9573. Min Act: -0.0000

Data Index: 160555 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.5858. Min Range: -1.5858

Max Act: 0.9762. Min Act: -0.0000

Data Index: 439757 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.5858. Min Range: -1.5858

Max Act: 0.9365. Min Act: -0.0000

Data Index: 134953 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 1.5858. Min Range: -1.5858

Max Act: 0.9877. Min Act: -0.0000

Data Index: 450118 (C4 (Web Text))

Max Activating Token Index: 281