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

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

Neuron 5180 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1045765 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0517. Min Act: -0.0000

Data Index: 366572 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0489. Min Act: -0.0000

Data Index: 767506 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0466. Min Act: -0.0000

Data Index: 391207 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1588680 (Python Code)

Max Activating Token Index: 476

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0394. Min Act: -0.0000

Data Index: 818199 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0448. Min Act: -0.0000

Data Index: 383131 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1538359 (Python Code)

Max Activating Token Index: 739

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0415. Min Act: -0.0000

Data Index: 616947 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1520775 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0387. Min Act: -0.0000

Data Index: 1465041 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1474871 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1586407 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1486765 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0323. Min Act: -0.0000

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0349. Min Act: -0.0000

Data Index: 525602 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1171908 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1651930 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1638167 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0304. Min Act: -0.0000

Data Index: 660782 (C4 (Web Text))

Max Activating Token Index: 392