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

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

Neuron 4142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0002

Data Index: 579155 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2936. Min Act: -0.0002

Data Index: 794598 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2685. Min Act: -0.0002

Data Index: 510049 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2671. Min Act: -0.0002

Data Index: 171714 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2571. Min Act: -0.0002

Data Index: 1359336 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2543. Min Act: -0.0002

Data Index: 1187199 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2511. Min Act: -0.0002

Data Index: 733097 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2506. Min Act: -0.0002

Data Index: 157123 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2405. Min Act: -0.0002

Data Index: 125648 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2357. Min Act: -0.0002

Data Index: 124686 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2432. Min Act: -0.0002

Data Index: 361773 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2334. Min Act: -0.0002

Data Index: 717772 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2397. Min Act: -0.0002

Data Index: 633878 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2381. Min Act: -0.0002

Data Index: 561226 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2357. Min Act: -0.0002

Data Index: 543415 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2248. Min Act: -0.0002

Data Index: 1118432 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2331. Min Act: -0.0002

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2334. Min Act: -0.0002

Data Index: 351199 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2230. Min Act: -0.0002

Data Index: 243725 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2215. Min Act: -0.0002

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 248