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

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

Neuron 4615 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.2071. Min Act: -0.0002

Data Index: 91780 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1652. Min Act: -0.0002

Data Index: 1199750 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1564. Min Act: -0.0002

Data Index: 444308 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0521. Min Act: -0.0002

Data Index: 1274595 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0358. Min Act: -0.0002

Data Index: 584719 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1392. Min Act: -0.0002

Data Index: 88296 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9660. Min Act: -0.0002

Data Index: 369044 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0004. Min Act: -0.0002

Data Index: 988236 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0646. Min Act: -0.0002

Data Index: 734167 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9525. Min Act: -0.0002

Data Index: 236769 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9080. Min Act: -0.0002

Data Index: 1045499 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0158. Min Act: -0.0002

Data Index: 950029 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9036. Min Act: -0.0002

Data Index: 1009834 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9402. Min Act: -0.0002

Data Index: 270634 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8444. Min Act: -0.0002

Data Index: 6927 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8827. Min Act: -0.0003

Data Index: 1196733 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8059. Min Act: -0.0003

Data Index: 1282154 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8797. Min Act: -0.0002

Data Index: 671215 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8814. Min Act: -0.0002

Data Index: 584461 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8535. Min Act: -0.0002

Data Index: 643826 (C4 (Web Text))

Max Activating Token Index: 880