Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3426 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1506424 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1551579 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1451116 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1653491 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1366268 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1561804 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1467941 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1507357 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1609558 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1589883 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1484845 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1460384 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1606200 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1622581 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1524832 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1610911 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1610721 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1573988 (Python Code)

Max Activating Token Index: 68

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1509205 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1592200 (Python Code)

Max Activating Token Index: 63