Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1262 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1359260 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1118097 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0003

Data Index: 459155 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1206068 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1011306 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0003

Data Index: 194892 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1250552 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1158891 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0002

Data Index: 21330 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1433884 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0003

Data Index: 979685 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0003

Data Index: 118473 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1307236 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0003

Data Index: 585828 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0003

Data Index: 215796 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0002

Data Index: 145458 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1267030 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0003

Data Index: 573199 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1213362 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1609101 (Python Code)

Max Activating Token Index: 650