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

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

Neuron 4320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.6618. Min Act: -0.0000

Data Index: 1493970 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.5824. Min Act: -0.0000

Data Index: 1438654 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1412883 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1513716 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1557671 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3243. Min Act: -0.0000

Data Index: 1651831 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1654783 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1529145 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1442236 (Python Code)

Max Activating Token Index: 184

Text #9

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1639248 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1588416 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1374268 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1615049 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1576509 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1462138 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1616239 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1561590 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1528337 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1427026 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1432285 (Python Code)

Max Activating Token Index: 742