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

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

Neuron 2326 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: 0.6755. Min Range: -0.6755

Max Act: 0.6755. Min Act: -0.0000

Data Index: 290285 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1022215 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5668. Min Act: -0.0001

Data Index: 284374 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5452. Min Act: -0.0001

Data Index: 359377 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5277. Min Act: -0.0001

Data Index: 1303807 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1274488 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5000. Min Act: -0.0000

Data Index: 414987 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1272812 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5449. Min Act: -0.0001

Data Index: 376077 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4847. Min Act: -0.0001

Data Index: 261738 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5014. Min Act: -0.0001

Data Index: 1184762 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4964. Min Act: -0.0000

Data Index: 181024 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5059. Min Act: -0.0000

Data Index: 62600 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4564. Min Act: -0.0001

Data Index: 400315 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4762. Min Act: -0.0000

Data Index: 525072 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4628. Min Act: -0.0001

Data Index: 819265 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4754. Min Act: -0.0000

Data Index: 288242 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4727. Min Act: -0.0000

Data Index: 9990 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4834. Min Act: -0.0000

Data Index: 532870 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4652. Min Act: -0.0001

Data Index: 209264 (C4 (Web Text))

Max Activating Token Index: 754