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

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

Neuron 1825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1091198 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1132887 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0452. Min Act: -0.0000

Data Index: 200089 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1582047 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1276217 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0353. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1051767 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0346. Min Act: -0.0000

Data Index: 778735 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0360. Min Act: -0.0000

Data Index: 788904 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1170782 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1034641 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0353. Min Act: -0.0000

Data Index: 750594 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1424952 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0365. Min Act: -0.0000

Data Index: 576617 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1093780 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0332. Min Act: -0.0000

Data Index: 250000 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0345. Min Act: -0.0000

Data Index: 331719 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1596009 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1389829 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0325. Min Act: -0.0000

Data Index: 785246 (C4 (Web Text))

Max Activating Token Index: 968