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

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

Neuron 583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0003

Data Index: 101886 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0437. Min Act: -0.0003

Data Index: 142431 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0412. Min Act: -0.0003

Data Index: 767576 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0411. Min Act: -0.0003

Data Index: 635559 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0376. Min Act: -0.0002

Data Index: 240876 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1191543 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0382. Min Act: -0.0003

Data Index: 493601 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0361. Min Act: -0.0002

Data Index: 545905 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1177241 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0326. Min Act: -0.0002

Data Index: 624948 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0325. Min Act: -0.0003

Data Index: 636700 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0312. Min Act: -0.0002

Data Index: 321178 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0324. Min Act: -0.0003

Data Index: 530806 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1187966 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0308. Min Act: -0.0003

Data Index: 147058 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0317. Min Act: -0.0003

Data Index: 55679 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0324. Min Act: -0.0003

Data Index: 377440 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0309. Min Act: -0.0003

Data Index: 16802 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0313. Min Act: -0.0003

Data Index: 219691 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0351. Min Act: -0.0003

Data Index: 231660 (C4 (Web Text))

Max Activating Token Index: 672