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

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

Neuron 2951 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3316. Min Act: -0.0000

Data Index: 478920 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3031. Min Act: -0.0000

Data Index: 153044 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2876. Min Act: -0.0000

Data Index: 108245 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2876. Min Act: -0.0000

Data Index: 973408 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1533201 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1285878 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2614. Min Act: -0.0000

Data Index: 142982 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1054266 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2492. Min Act: -0.0000

Data Index: 244157 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1422862 (Python Code)

Max Activating Token Index: 495

Text #10

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2433. Min Act: -0.0000

Data Index: 566397 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2426. Min Act: -0.0000

Data Index: 222658 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2368. Min Act: -0.0000

Data Index: 29874 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1392384 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1414295 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2366. Min Act: -0.0000

Data Index: 619827 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2264. Min Act: -0.0000

Data Index: 357616 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2311. Min Act: -0.0000

Data Index: 797899 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1439417 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2312. Min Act: -0.0000

Data Index: 414039 (C4 (Web Text))

Max Activating Token Index: 692