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

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

Neuron 5693 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0713. Min Range: -6.0713

Max Act: 6.0713. Min Act: -0.0000

Data Index: 1533279 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.9501. Min Act: -0.0000

Data Index: 1601291 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.7178. Min Act: -0.0000

Data Index: 1651037 (Python Code)

Max Activating Token Index: 201

Text #3

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.3206. Min Act: -0.0000

Data Index: 1361792 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.3555. Min Act: -0.0000

Data Index: 1601929 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.2334. Min Act: -0.0000

Data Index: 1653536 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.4095. Min Act: -0.0000

Data Index: 1605869 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 6.0713. Min Range: -6.0713

Max Act: 4.6369. Min Act: -0.0000

Data Index: 1608755 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.3227. Min Act: -0.0000

Data Index: 1467687 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.5237. Min Act: -0.0000

Data Index: 1394422 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.3271. Min Act: -0.0000

Data Index: 1615084 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.3903. Min Act: -0.0000

Data Index: 1573766 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.1770. Min Act: -0.0000

Data Index: 1635709 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 6.0713. Min Range: -6.0713

Max Act: 4.9855. Min Act: -0.0000

Data Index: 1469348 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 6.0713. Min Range: -6.0713

Max Act: 4.9552. Min Act: -0.0000

Data Index: 1500840 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.0839. Min Act: -0.0000

Data Index: 1595319 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.2407. Min Act: -0.0000

Data Index: 1403159 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 6.0713. Min Range: -6.0713

Max Act: 5.1822. Min Act: -0.0000

Data Index: 1449887 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 6.0713. Min Range: -6.0713

Max Act: 4.9911. Min Act: -0.0000

Data Index: 1490784 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 6.0713. Min Range: -6.0713

Max Act: 4.7571. Min Act: -0.0000

Data Index: 1440993 (Python Code)

Max Activating Token Index: 54