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

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

Neuron 4831 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1468008 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1170261 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0030. Min Act: -0.0002

Data Index: 885486 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0029. Min Act: -0.0003

Data Index: 606548 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1073476 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0028. Min Act: -0.0002

Data Index: 294820 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1008491 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0027. Min Act: -0.0003

Data Index: 533753 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0026. Min Act: -0.0003

Data Index: 117028 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0027. Min Act: -0.0002

Data Index: 444934 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0026. Min Act: -0.0003

Data Index: 112937 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0026. Min Act: -0.0002

Data Index: 949268 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1158082 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0026. Min Act: -0.0003

Data Index: 931590 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0025. Min Act: -0.0003

Data Index: 340116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0024. Min Act: -0.0002

Data Index: 330877 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0025. Min Act: -0.0002

Data Index: 784628 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0027. Min Act: -0.0003

Data Index: 1282551 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0025. Min Act: -0.0003

Data Index: 154850 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0039. Min Range: -0.0039

Max Act: 0.0025. Min Act: -0.0002

Data Index: 188184 (C4 (Web Text))

Max Activating Token Index: 15