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

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

Neuron 1759 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: 0.0036. Min Range: -0.0036

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1654564 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1619335 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0032. Min Act: -0.0005

Data Index: 303730 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1620333 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1653210 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0031. Min Act: -0.0005

Data Index: 272311 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1388786 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1651171 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1583696 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1618153 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1429348 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1653154 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1411095 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1118772 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1437133 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1456154 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1230337 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1411252 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1446834 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 1402611 (Python Code)

Max Activating Token Index: 234