Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1339 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1411302 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0068. Min Act: -0.0005

Data Index: 1385670 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1408898 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1365666 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0005

Data Index: 225986 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1397695 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1399891 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 808344 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 639242 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1463581 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1433852 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1540579 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1555940 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0005

Data Index: 960200 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 776112 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1309896 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0005

Data Index: 141901 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1434950 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1418745 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0005

Data Index: 155906 (C4 (Web Text))

Max Activating Token Index: 97