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

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

Neuron 4512 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: 0.4723. Min Range: -0.4723

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1304566 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1188713 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1200577 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3221. Min Act: -0.0000

Data Index: 967419 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2950. Min Act: -0.0000

Data Index: 534585 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2603. Min Act: -0.0000

Data Index: 283953 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2519. Min Act: -0.0000

Data Index: 287950 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2331. Min Act: -0.0000

Data Index: 293891 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2291. Min Act: -0.0000

Data Index: 521266 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2257. Min Act: -0.0000

Data Index: 354736 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2151. Min Act: -0.0000

Data Index: 938217 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2192. Min Act: -0.0000

Data Index: 384754 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2016. Min Act: -0.0000

Data Index: 107270 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.1881. Min Act: -0.0000

Data Index: 669743 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.1931. Min Act: -0.0000

Data Index: 496548 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.1989. Min Act: -0.0000

Data Index: 155030 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1290554 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.1890. Min Act: -0.0000

Data Index: 262317 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.2007. Min Act: -0.0000

Data Index: 815470 (C4 (Web Text))

Max Activating Token Index: 613