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

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

Neuron 3532 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5536. Min Act: -0.0003

Data Index: 96942 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5268. Min Act: -0.0002

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5266. Min Act: -0.0002

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5171. Min Act: -0.0003

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4897. Min Act: -0.0002

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5009. Min Act: -0.0002

Data Index: 767166 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4966. Min Act: -0.0002

Data Index: 119879 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4899. Min Act: -0.0002

Data Index: 993065 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4873. Min Act: -0.0002

Data Index: 924753 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4721. Min Act: -0.0002

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4565. Min Act: -0.0003

Data Index: 1182008 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4560. Min Act: -0.0002

Data Index: 666970 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4688. Min Act: -0.0002

Data Index: 1048960 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4641. Min Act: -0.0002

Data Index: 648919 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4614. Min Act: -0.0003

Data Index: 1061974 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4608. Min Act: -0.0002

Data Index: 1350238 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4379. Min Act: -0.0002

Data Index: 850193 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4324. Min Act: -0.0002

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4455. Min Act: -0.0002

Data Index: 928795 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4369. Min Act: -0.0002

Data Index: 405127 (C4 (Web Text))

Max Activating Token Index: 162