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

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

Neuron 1377 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2397. Min Range: -3.2397

Max Act: 3.0511. Min Act: -0.0000

Data Index: 1626915 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 3.2397. Min Range: -3.2397

Max Act: 3.2397. Min Act: -0.0000

Data Index: 1460612 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.4531. Min Act: -0.0000

Data Index: 480307 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.6325. Min Act: -0.0000

Data Index: 1534911 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.4636. Min Act: -0.0000

Data Index: 765321 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2877. Min Act: -0.0000

Data Index: 1572728 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2588. Min Act: -0.0000

Data Index: 1420999 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.3538. Min Act: -0.0000

Data Index: 1554627 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.4338. Min Act: -0.0000

Data Index: 1468108 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.3168. Min Act: -0.0000

Data Index: 1118197 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2473. Min Act: -0.0000

Data Index: 4688 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2767. Min Act: -0.0000

Data Index: 1249696 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2739. Min Act: -0.0000

Data Index: 7701 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.3816. Min Act: -0.0000

Data Index: 67759 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2206. Min Act: -0.0000

Data Index: 858827 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1330945 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2202. Min Act: -0.0000

Data Index: 278278 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1480464 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.1933. Min Act: -0.0000

Data Index: 55272 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 3.2397. Min Range: -3.2397

Max Act: 2.1820. Min Act: -0.0000

Data Index: 868927 (C4 (Web Text))

Max Activating Token Index: 7