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

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

Neuron 1681 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: 0.6073. Min Range: -0.6073

Max Act: 0.6073. Min Act: -0.0004

Data Index: 785796 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5527. Min Act: -0.0004

Data Index: 78803 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4926. Min Act: -0.0004

Data Index: 1032819 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5182. Min Act: -0.0004

Data Index: 885927 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5925. Min Act: -0.0004

Data Index: 286267 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5330. Min Act: -0.0004

Data Index: 1306504 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5656. Min Act: -0.0004

Data Index: 1098648 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5577. Min Act: -0.0004

Data Index: 826546 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5544. Min Act: -0.0004

Data Index: 1173915 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5644. Min Act: -0.0004

Data Index: 110246 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5261. Min Act: -0.0004

Data Index: 849642 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5240. Min Act: -0.0004

Data Index: 47705 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5704. Min Act: -0.0004

Data Index: 1242172 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5149. Min Act: -0.0004

Data Index: 871155 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4952. Min Act: -0.0004

Data Index: 1007878 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4699. Min Act: -0.0004

Data Index: 406950 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4867. Min Act: -0.0004

Data Index: 191184 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4720. Min Act: -0.0004

Data Index: 419105 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5214. Min Act: -0.0004

Data Index: 955344 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4854. Min Act: -0.0004

Data Index: 145919 (C4 (Web Text))

Max Activating Token Index: 413