Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1067 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1139145 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0003

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0003

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1462265 (Python Code)

Max Activating Token Index: 174

Text #4

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0003

Data Index: 56957 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 1147092 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1651972 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1127137 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 878385 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 1174668 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 168218 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1541653 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1475483 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 132054 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 1197117 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 1045308 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 556154 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1027784 (C4 (Web Text))

Max Activating Token Index: 208