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

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

Neuron 3165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5840. Min Act: -0.0000

Data Index: 62560 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.6193. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5859. Min Act: -0.0000

Data Index: 465187 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.6010. Min Act: -0.0000

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5579. Min Act: -0.0000

Data Index: 116509 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5709. Min Act: -0.0000

Data Index: 963782 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1250344 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5095. Min Act: -0.0000

Data Index: 938279 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5686. Min Act: -0.0000

Data Index: 534740 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5270. Min Act: -0.0000

Data Index: 612021 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5314. Min Act: -0.0000

Data Index: 654150 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5390. Min Act: -0.0000

Data Index: 704209 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4776. Min Act: -0.0000

Data Index: 407409 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1057601 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5159. Min Act: -0.0000

Data Index: 736876 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1549257 (Python Code)

Max Activating Token Index: 598

Text #16

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4948. Min Act: -0.0000

Data Index: 294592 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5102. Min Act: -0.0000

Data Index: 834864 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1306120 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4603. Min Act: -0.0000

Data Index: 223638 (C4 (Web Text))

Max Activating Token Index: 445