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

Dataset: The Pile

Neuron 1466 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.7580. Min Act: -0.0000

Data Index: 1540897 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 8.0062. Min Range: -8.0062

Max Act: 8.0062. Min Act: -0.0000

Data Index: 771506 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.5643. Min Act: -0.0000

Data Index: 779248 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.6131. Min Act: -0.0000

Data Index: 1630027 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.0231. Min Act: -0.0000

Data Index: 298564 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.3881. Min Act: -0.0000

Data Index: 798103 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.0148. Min Act: -0.0000

Data Index: 217559 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.2009. Min Act: -0.0000

Data Index: 336374 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.2107. Min Act: -0.0000

Data Index: 392528 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.3037. Min Act: -0.0000

Data Index: 78091 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.0879. Min Act: -0.0000

Data Index: 1283688 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.1992. Min Act: -0.0000

Data Index: 1103564 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.1765. Min Act: -0.0000

Data Index: 974234 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 8.0062. Min Range: -8.0062

Max Act: 6.7882. Min Act: -0.0000

Data Index: 1474010 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.1520. Min Act: -0.0000

Data Index: 779948 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 8.0062. Min Range: -8.0062

Max Act: 6.9583. Min Act: -0.0000

Data Index: 1471338 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 8.0062. Min Range: -8.0062

Max Act: 6.7459. Min Act: -0.0000

Data Index: 620978 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.1010. Min Act: -0.0000

Data Index: 1250712 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 8.0062. Min Range: -8.0062

Max Act: 7.0343. Min Act: -0.0000

Data Index: 890974 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 8.0062. Min Range: -8.0062

Max Act: 6.6566. Min Act: -0.0000

Data Index: 1956843 (The Pile)

Max Activating Token Index: 28