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

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

Neuron 308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3998. Min Act: 0.0000

Data Index: 539363 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1356098 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2822. Min Act: -0.0000

Data Index: 931082 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2669. Min Act: -0.0000

Data Index: 647160 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2454. Min Act: -0.0000

Data Index: 885899 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2340. Min Act: -0.0000

Data Index: 81460 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1006165 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2529. Min Act: -0.0000

Data Index: 413402 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2256. Min Act: -0.0000

Data Index: 846923 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2247. Min Act: -0.0000

Data Index: 91092 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2316. Min Act: 0.0000

Data Index: 1019353 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1007082 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2308. Min Act: -0.0000

Data Index: 673018 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2181. Min Act: -0.0000

Data Index: 510313 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2247. Min Act: -0.0000

Data Index: 285434 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2109. Min Act: -0.0000

Data Index: 732901 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2147. Min Act: 0.0001

Data Index: 318823 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2192. Min Act: -0.0000

Data Index: 690725 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1073017 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1282266 (C4 (Web Text))

Max Activating Token Index: 90