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

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

Neuron 5937 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: 0.4202. Min Range: -0.4202

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1454146 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1532659 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4182. Min Act: -0.0001

Data Index: 1524565 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1579. Min Act: -0.0001

Data Index: 923728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2718. Min Act: -0.0000

Data Index: 326456 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1488514 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1160552 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1463118 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1568352 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1383047 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1505388 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1486284 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1524394 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1497401 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1442307 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2614. Min Act: -0.0001

Data Index: 1443887 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1570464 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.0578. Min Act: -0.0001

Data Index: 310344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1430075 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1364438 (Python Code)

Max Activating Token Index: 1023