Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2611 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0003

Data Index: 455583 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1201006 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1209542 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0060. Min Act: -0.0003

Data Index: 853813 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0057. Min Act: -0.0003

Data Index: 341068 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0056. Min Act: -0.0003

Data Index: 528996 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0056. Min Act: -0.0003

Data Index: 600949 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0055. Min Act: -0.0003

Data Index: 43436 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1300675 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0003

Data Index: 835700 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0003

Data Index: 230802 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0049. Min Act: -0.0003

Data Index: 383166 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1358617 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0002

Data Index: 866157 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0047. Min Act: -0.0003

Data Index: 858874 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0048. Min Act: -0.0002

Data Index: 965268 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0046. Min Act: -0.0003

Data Index: 885588 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0047. Min Act: -0.0003

Data Index: 770514 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1003524 (C4 (Web Text))

Max Activating Token Index: 879