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

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

Neuron 1422 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: 4.6645. Min Range: -4.6645

Max Act: 4.6645. Min Act: -0.0000

Data Index: 1493872 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.4784. Min Act: -0.0000

Data Index: 1584314 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.4022. Min Act: -0.0000

Data Index: 1437717 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.1169. Min Act: -0.0000

Data Index: 1402952 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.9558. Min Act: -0.0000

Data Index: 1590683 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.2309. Min Act: -0.0000

Data Index: 1428627 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.9941. Min Act: -0.0000

Data Index: 1416819 (Python Code)

Max Activating Token Index: 512

Text #7

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.9009. Min Act: -0.0000

Data Index: 1461821 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.6823. Min Act: -0.0000

Data Index: 1456426 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.8435. Min Act: -0.0000

Data Index: 1535783 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.1053. Min Act: -0.0000

Data Index: 1583673 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.0949. Min Act: -0.0000

Data Index: 1633775 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 4.6645. Min Range: -4.6645

Max Act: 4.0478. Min Act: -0.0000

Data Index: 1423628 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.6274. Min Act: -0.0000

Data Index: 1557754 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.6600. Min Act: -0.0000

Data Index: 1466036 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.5186. Min Act: -0.0000

Data Index: 1550258 (Python Code)

Max Activating Token Index: 628

Text #16

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.3493. Min Act: -0.0000

Data Index: 1526652 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.3163. Min Act: -0.0000

Data Index: 1391387 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.3091. Min Act: -0.0000

Data Index: 1624081 (Python Code)

Max Activating Token Index: 794

Text #19

Max Range: 4.6645. Min Range: -4.6645

Max Act: 3.4439. Min Act: -0.0000

Data Index: 1594866 (Python Code)

Max Activating Token Index: 493