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

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

Neuron 1198 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3466. Min Act: -0.0000

Data Index: 39483 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3209. Min Act: 0.0000

Data Index: 709678 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2495. Min Act: -0.0000

Data Index: 23734 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1220674 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2209. Min Act: -0.0000

Data Index: 104643 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1034293 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2335. Min Act: -0.0000

Data Index: 4425 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2216. Min Act: -0.0000

Data Index: 809408 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2011. Min Act: -0.0000

Data Index: 802831 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2229. Min Act: -0.0000

Data Index: 694932 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2153. Min Act: -0.0000

Data Index: 162620 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2091. Min Act: -0.0000

Data Index: 228296 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1985. Min Act: -0.0000

Data Index: 401483 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1913. Min Act: -0.0000

Data Index: 775120 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1808. Min Act: -0.0000

Data Index: 597830 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1891. Min Act: -0.0000

Data Index: 548900 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1870. Min Act: -0.0000

Data Index: 966966 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1850. Min Act: -0.0000

Data Index: 104049 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1163924 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1722. Min Act: -0.0000

Data Index: 49076 (C4 (Web Text))

Max Activating Token Index: 280