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

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

Neuron 207 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1477431 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1549232 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1485710 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1460259 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1369914 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1442738 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1485308 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1552044 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1412934 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1609141 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1495088 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1452369 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1570269 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1435064 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1479116 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1373404 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1394698 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1416652 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1542871 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1439555 (Python Code)

Max Activating Token Index: 23