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

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

Neuron 4362 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0002

Data Index: 984378 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0084. Min Act: -0.0002

Data Index: 548744 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0080. Min Act: -0.0002

Data Index: 287830 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0080. Min Act: -0.0002

Data Index: 613750 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0080. Min Act: -0.0002

Data Index: 959093 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0076. Min Act: -0.0002

Data Index: 687606 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0075. Min Act: -0.0002

Data Index: 530959 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0075. Min Act: -0.0002

Data Index: 689003 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1184529 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1223127 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0072. Min Act: -0.0002

Data Index: 799146 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0073. Min Act: -0.0002

Data Index: 426930 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0073. Min Act: -0.0002

Data Index: 419323 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0072. Min Act: -0.0002

Data Index: 340657 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0002

Data Index: 4499 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0072. Min Act: -0.0002

Data Index: 132011 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0002

Data Index: 216810 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0002

Data Index: 163888 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0002

Data Index: 696241 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1032276 (C4 (Web Text))

Max Activating Token Index: 262