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

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

Neuron 87 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2719. Min Act: -0.0000

Data Index: 85041 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2434. Min Act: -0.0001

Data Index: 604060 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1508902 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1501882 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1511777 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2401. Min Act: -0.0001

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1522395 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1041250 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2292. Min Act: -0.0001

Data Index: 282178 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1493937 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1604155 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1376375 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1422840 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1436313 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1401160 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1425039 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2074. Min Act: -0.0000

Data Index: 13178 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1501240 (Python Code)

Max Activating Token Index: 1010

Text #18

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1479777 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1548284 (Python Code)

Max Activating Token Index: 88