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

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

Neuron 3610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.6220. Min Act: -0.0000

Data Index: 144016 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1289049 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3629. Min Act: -0.0001

Data Index: 1115559 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1285406 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3209. Min Act: -0.0001

Data Index: 168148 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3420. Min Act: -0.0000

Data Index: 342277 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2908. Min Act: -0.0000

Data Index: 194915 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2737. Min Act: -0.0001

Data Index: 514003 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3153. Min Act: -0.0000

Data Index: 100102 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2888. Min Act: -0.0000

Data Index: 784347 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3199. Min Act: -0.0001

Data Index: 611727 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2387. Min Act: -0.0000

Data Index: 724135 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3313. Min Act: -0.0001

Data Index: 1042588 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.3007. Min Act: -0.0001

Data Index: 980958 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2622. Min Act: -0.0001

Data Index: 44548 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2503. Min Act: -0.0000

Data Index: 624020 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2042. Min Act: -0.0001

Data Index: 333738 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2435. Min Act: -0.0000

Data Index: 939184 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1075394 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 1.6220. Min Range: -1.6220

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1340776 (C4 (Web Text))

Max Activating Token Index: 790