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

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

Neuron 1802 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: 1.5135. Min Range: -1.5135

Max Act: 1.5135. Min Act: -0.0001

Data Index: 1574246 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.4135. Min Act: -0.0001

Data Index: 1536324 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.4135. Min Act: -0.0001

Data Index: 1450454 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1643053 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1608194 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1543449 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1544415 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1518060 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1939. Min Act: -0.0002

Data Index: 1635356 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2185. Min Act: -0.0001

Data Index: 1629288 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1834. Min Act: -0.0001

Data Index: 1554207 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1798. Min Act: -0.0001

Data Index: 1483339 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2487. Min Act: -0.0001

Data Index: 1423488 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2126. Min Act: -0.0001

Data Index: 1476993 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.2050. Min Act: -0.0001

Data Index: 1418455 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1793. Min Act: -0.0001

Data Index: 1571218 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1793. Min Act: -0.0001

Data Index: 1423916 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1474. Min Act: -0.0001

Data Index: 1381648 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1128. Min Act: -0.0001

Data Index: 1466426 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.5135. Min Range: -1.5135

Max Act: 1.1178. Min Act: -0.0001

Data Index: 1626329 (Python Code)

Max Activating Token Index: 5