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

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

Neuron 4644 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4087. Min Act: -0.0000

Data Index: 380682 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3000. Min Act: -0.0000

Data Index: 573713 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2742. Min Act: -0.0000

Data Index: 20007 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2914. Min Act: -0.0000

Data Index: 435864 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2290. Min Act: -0.0000

Data Index: 7999 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2381. Min Act: -0.0000

Data Index: 344863 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2391. Min Act: -0.0000

Data Index: 820029 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2256. Min Act: 0.0000

Data Index: 143630 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2295. Min Act: 0.0000

Data Index: 1133660 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2398. Min Act: -0.0000

Data Index: 428791 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2121. Min Act: -0.0000

Data Index: 974752 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1130321 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1342126 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2014. Min Act: -0.0000

Data Index: 813602 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2087. Min Act: -0.0000

Data Index: 575330 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2082. Min Act: -0.0000

Data Index: 254396 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2186. Min Act: -0.0000

Data Index: 307902 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1070987 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2044. Min Act: 0.0000

Data Index: 646705 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.1966. Min Act: -0.0000

Data Index: 671231 (C4 (Web Text))

Max Activating Token Index: 466