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

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

Neuron 536 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3405. Min Act: -0.0000

Data Index: 629292 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3157. Min Act: -0.0000

Data Index: 919017 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3391. Min Act: -0.0000

Data Index: 205019 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3291. Min Act: -0.0000

Data Index: 792135 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0000

Data Index: 248988 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1627394 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2532. Min Act: -0.0000

Data Index: 844218 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1934. Min Act: -0.0000

Data Index: 160445 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1138190 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1363312 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1312447 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1581656 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1409072 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1731. Min Act: -0.0000

Data Index: 839243 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1667. Min Act: -0.0000

Data Index: 457118 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1828. Min Act: -0.0000

Data Index: 307650 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1634737 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1540131 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1433761 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1475003 (Python Code)

Max Activating Token Index: 326