Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.4054. Min Act: -0.0000

Data Index: 1646488 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.3584. Min Act: -0.0000

Data Index: 1621888 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.1776. Min Act: -0.0000

Data Index: 1392288 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.0116. Min Act: -0.0000

Data Index: 1491184 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.1821. Min Act: -0.0000

Data Index: 1645022 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 3.4054. Min Range: -3.4054

Max Act: 3.3118. Min Act: -0.0000

Data Index: 1525406 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.9553. Min Act: -0.0000

Data Index: 1454222 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.9008. Min Act: -0.0000

Data Index: 1609015 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.7057. Min Act: -0.0000

Data Index: 1597519 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.6226. Min Act: -0.0000

Data Index: 1634890 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.4752. Min Act: -0.0000

Data Index: 1575820 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.5938. Min Act: -0.0000

Data Index: 1647427 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.2847. Min Act: -0.0000

Data Index: 670324 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.5017. Min Act: -0.0000

Data Index: 1622033 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1417482 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1416614 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1505210 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 3.4054. Min Range: -3.4054

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1522699 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.1208. Min Act: -0.0000

Data Index: 1381941 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 3.4054. Min Range: -3.4054

Max Act: 2.2034. Min Act: -0.0000

Data Index: 1636158 (Python Code)

Max Activating Token Index: 503