Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 634 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0005

Data Index: 844460 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1128927 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 297546 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0004

Data Index: 1123812 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 347305 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0005

Data Index: 599067 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0005

Data Index: 274983 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 76376 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 802187 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0004

Data Index: 341621 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1013830 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1038836 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1595190 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1408858 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0004

Data Index: 574139 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1224464 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0004

Data Index: 433903 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0004

Data Index: 70800 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0005

Data Index: 68163 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0005

Data Index: 913908 (C4 (Web Text))

Max Activating Token Index: 291