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

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

Neuron 2006 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5570. Min Act: -0.0001

Data Index: 1619921 (Python Code)

Max Activating Token Index: 979

Text #1

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6557. Min Act: -0.0001

Data Index: 1621458 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6322. Min Act: -0.0001

Data Index: 1408292 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6396. Min Act: -0.0001

Data Index: 1537622 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6016. Min Act: -0.0001

Data Index: 1465471 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5839. Min Act: -0.0001

Data Index: 1539480 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5633. Min Act: -0.0001

Data Index: 1473423 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6530. Min Act: -0.0001

Data Index: 1413472 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.4973. Min Act: -0.0001

Data Index: 1389294 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5010. Min Act: -0.0002

Data Index: 1645598 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5816. Min Act: -0.0001

Data Index: 1399459 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5214. Min Act: -0.0001

Data Index: 1574850 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5186. Min Act: -0.0001

Data Index: 1564752 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.4157. Min Act: -0.0001

Data Index: 1614209 (Python Code)

Max Activating Token Index: 919

Text #14

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5968. Min Act: -0.0001

Data Index: 1645850 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6357. Min Act: -0.0001

Data Index: 1552546 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.4054. Min Act: -0.0001

Data Index: 1434379 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5482. Min Act: -0.0002

Data Index: 1365280 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5825. Min Act: -0.0001

Data Index: 1592433 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.4845. Min Act: -0.0001

Data Index: 1653317 (Python Code)

Max Activating Token Index: 39