Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1765 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0867. Min Act: -0.0004

Data Index: 708594 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0883. Min Act: -0.0004

Data Index: 1053685 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0869. Min Act: -0.0004

Data Index: 1307113 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0879. Min Act: -0.0004

Data Index: 848551 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0889. Min Act: -0.0004

Data Index: 659903 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0827. Min Act: -0.0004

Data Index: 335476 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0874. Min Act: -0.0004

Data Index: 272650 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0803. Min Act: -0.0004

Data Index: 705464 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0897. Min Act: -0.0004

Data Index: 487794 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0895. Min Act: -0.0004

Data Index: 865423 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0862. Min Act: -0.0004

Data Index: 455977 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0794. Min Act: -0.0004

Data Index: 757623 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0788. Min Act: -0.0004

Data Index: 820548 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0791. Min Act: -0.0004

Data Index: 1331617 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0792. Min Act: -0.0004

Data Index: 56303 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0753. Min Act: -0.0004

Data Index: 644737 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0815. Min Act: -0.0004

Data Index: 921386 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0004

Data Index: 240529 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0847. Min Act: -0.0004

Data Index: 712154 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0720. Min Act: -0.0004

Data Index: 485199 (C4 (Web Text))

Max Activating Token Index: 664