Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4471 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.3637. Min Act: -0.0001

Data Index: 1398459 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.2135. Min Act: -0.0001

Data Index: 1448466 (Python Code)

Max Activating Token Index: 572

Text #2

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1926. Min Act: -0.0001

Data Index: 1543530 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1951. Min Act: -0.0001

Data Index: 1492610 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1341. Min Act: -0.0001

Data Index: 1434735 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1556968 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.0409. Min Act: -0.0001

Data Index: 1593921 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9981. Min Act: -0.0001

Data Index: 1480934 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1403545 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9042. Min Act: -0.0001

Data Index: 1598903 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9446. Min Act: -0.0001

Data Index: 1641987 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.0202. Min Act: -0.0001

Data Index: 1492259 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 1.3637. Min Range: -1.3637

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1605156 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9827. Min Act: -0.0001

Data Index: 1599584 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1605377 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1594348 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9264. Min Act: -0.0001

Data Index: 1569732 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8936. Min Act: -0.0001

Data Index: 1603804 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1445617 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.3637. Min Range: -1.3637

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1524130 (Python Code)

Max Activating Token Index: 15