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

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

Neuron 744 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: 1.1468. Min Range: -1.1468

Max Act: 1.1468. Min Act: -0.0001

Data Index: 1532614 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1374522 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1626037 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1369186 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1440718 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7983. Min Act: -0.0001

Data Index: 1652050 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7730. Min Act: -0.0001

Data Index: 1534080 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7719. Min Act: -0.0001

Data Index: 1418367 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1395201 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7826. Min Act: -0.0001

Data Index: 1535163 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1554287 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1406979 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7298. Min Act: -0.0001

Data Index: 1642707 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1372817 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1524456 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1417084 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7464. Min Act: -0.0001

Data Index: 1521297 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1457053 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.7695. Min Act: -0.0001

Data Index: 1498951 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1547897 (Python Code)

Max Activating Token Index: 127