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

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

Neuron 2362 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.1607. Min Act: -0.0001

Data Index: 1063039 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1023268 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9914. Min Act: -0.0000

Data Index: 480325 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1098378 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9244. Min Act: -0.0000

Data Index: 770387 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8993. Min Act: -0.0000

Data Index: 168705 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8589. Min Act: -0.0000

Data Index: 91767 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8702. Min Act: -0.0000

Data Index: 550568 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1159413 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1321440 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1354373 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7958. Min Act: -0.0000

Data Index: 183445 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8721. Min Act: -0.0001

Data Index: 936480 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8235. Min Act: -0.0000

Data Index: 234105 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8320. Min Act: -0.0000

Data Index: 213983 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7848. Min Act: -0.0000

Data Index: 858230 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8279. Min Act: -0.0000

Data Index: 14336 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8571. Min Act: -0.0001

Data Index: 522689 (C4 (Web Text))

Max Activating Token Index: 789