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

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

Neuron 1329 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2547. Min Act: -0.0001

Data Index: 322220 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1392887 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2254. Min Act: -0.0000

Data Index: 664434 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1551082 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1637302 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2071. Min Act: -0.0001

Data Index: 626549 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1529785 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1613086 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2008. Min Act: -0.0001

Data Index: 661980 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1635258 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1446204 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1584940 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1583222 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1629614 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1505440 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1880. Min Act: -0.0001

Data Index: 1655589 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1798. Min Act: -0.0001

Data Index: 437314 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1428615 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1581582 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1786. Min Act: -0.0001

Data Index: 573617 (C4 (Web Text))

Max Activating Token Index: 862