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

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

Neuron 970 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: 1.8326. Min Range: -1.8326

Max Act: 1.8326. Min Act: -0.0000

Data Index: 1654739 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1643535 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1458108 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1375842 (Python Code)

Max Activating Token Index: 787

Text #4

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1633306 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1368240 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1420934 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1378010 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1403774 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1513251 (Python Code)

Max Activating Token Index: 724

Text #10

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1369896 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1376990 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1407433 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1512527 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1388353 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1410056 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1488887 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1650538 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1294485 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.8326. Min Range: -1.8326

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1518851 (Python Code)

Max Activating Token Index: 133