Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 356 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1199606 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 26552 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1083876 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 537187 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 95545 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1076876 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1356457 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0019. Min Act: -0.0006

Data Index: 882382 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 1078150 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 1177900 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 123721 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 563852 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 1075142 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 1005821 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 278564 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0017. Min Act: -0.0006

Data Index: 1167099 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0017. Min Act: -0.0006

Data Index: 1270986 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0018. Min Act: -0.0006

Data Index: 63712 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0017. Min Act: -0.0006

Data Index: 1113876 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0017. Min Act: -0.0006

Data Index: 152367 (C4 (Web Text))

Max Activating Token Index: 241