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

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

Neuron 2785 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0003

Data Index: 401480 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1188676 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0101. Min Act: -0.0004

Data Index: 145799 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0100. Min Act: -0.0003

Data Index: 175260 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0100. Min Act: -0.0004

Data Index: 323925 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0099. Min Act: -0.0003

Data Index: 211395 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0004

Data Index: 628630 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0004

Data Index: 1106237 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0003

Data Index: 907861 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1196669 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1029630 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0003

Data Index: 766503 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0099. Min Act: -0.0004

Data Index: 1233018 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0095. Min Act: -0.0003

Data Index: 897285 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0003

Data Index: 545478 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0004

Data Index: 1050076 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 15644 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1326133 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 931514 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1183221 (C4 (Web Text))

Max Activating Token Index: 487