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

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

Neuron 5886 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3747. Min Act: -0.0002

Data Index: 1568588 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2602. Min Act: -0.0002

Data Index: 607280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2258. Min Act: -0.0002

Data Index: 635401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2170. Min Act: -0.0002

Data Index: 590003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2166. Min Act: -0.0002

Data Index: 1326609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1905. Min Act: -0.0002

Data Index: 166492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1837. Min Act: -0.0002

Data Index: 277687 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1797. Min Act: -0.0002

Data Index: 1233715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1705. Min Act: -0.0002

Data Index: 1009655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 889

Text #10

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1647. Min Act: -0.0002

Data Index: 811548 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1793. Min Act: -0.0002

Data Index: 1413459 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1444. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1426. Min Act: -0.0002

Data Index: 772870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1079049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1017341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1319. Min Act: -0.0002

Data Index: 950698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1493. Min Act: -0.0002

Data Index: 138356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1139484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1377. Min Act: -0.0002

Data Index: 228418 (C4 (Web Text))

Max Activating Token Index: 1023