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

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

Neuron 5540 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: 1.9371. Min Range: -1.9371

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1400112 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1635937 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1531667 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1365107 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1450519 (Python Code)

Max Activating Token Index: 666

Text #7

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1583753 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.4539. Min Act: -0.0000

Data Index: 1404537 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.3617. Min Act: -0.0000

Data Index: 404787 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1497741 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1265598 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1631518 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1182466 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.9371. Min Range: -1.9371

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1042061 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.9371. Min Range: -1.9371

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1401076 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 1.9371. Min Range: -1.9371

Max Act: 0.9347. Min Act: 0.0000

Data Index: 1362632 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 1.9371. Min Range: -1.9371

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1587980 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.9371. Min Range: -1.9371

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1606901 (Python Code)

Max Activating Token Index: 514

Text #19

Max Range: 1.9371. Min Range: -1.9371

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 811