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

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

Neuron 580 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: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0003

Data Index: 207449 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0003

Data Index: 246199 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0003

Data Index: 634388 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0020. Min Act: -0.0003

Data Index: 525551 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0017. Min Act: -0.0002

Data Index: 460716 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0017. Min Act: -0.0003

Data Index: 179493 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0017. Min Act: -0.0002

Data Index: 920526 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1219397 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1226036 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1112244 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1310069 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0016. Min Act: -0.0003

Data Index: 565200 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0002

Data Index: 594286 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 967780 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 48146 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 87616 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 969367 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1290966 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 860186 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0015. Min Act: -0.0003

Data Index: 300280 (C4 (Web Text))

Max Activating Token Index: 251