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

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

Neuron 251 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: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0002

Data Index: 136322 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0921. Min Act: -0.0002

Data Index: 724865 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0863. Min Act: -0.0002

Data Index: 217759 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1118681 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1167768 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0713. Min Act: -0.0002

Data Index: 777968 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0694. Min Act: -0.0002

Data Index: 912505 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0732. Min Act: -0.0002

Data Index: 660073 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0770. Min Act: -0.0002

Data Index: 106863 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0690. Min Act: -0.0002

Data Index: 416601 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0715. Min Act: -0.0002

Data Index: 126534 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0674. Min Act: -0.0002

Data Index: 637000 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1234119 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0670. Min Act: -0.0002

Data Index: 571069 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0657. Min Act: -0.0002

Data Index: 745107 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0641. Min Act: -0.0002

Data Index: 354674 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1149999 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0721. Min Act: -0.0002

Data Index: 734486 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1149251 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0670. Min Act: -0.0002

Data Index: 764032 (C4 (Web Text))

Max Activating Token Index: 571