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

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

Neuron 2145 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: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0003

Data Index: 608952 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0003

Data Index: 574581 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0003

Data Index: 277318 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1054710 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0003

Data Index: 685821 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 582031 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 197020 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 149306 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 209666 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 741990 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 292733 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 374719 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 413037 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 408166 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 1294127 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 1225463 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 703559 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0003

Data Index: 963694 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0003. Min Act: -0.0003

Data Index: 261609 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0003. Min Act: -0.0003

Data Index: 503484 (C4 (Web Text))

Max Activating Token Index: 211