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

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

Neuron 1603 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.3029. Min Act: -0.0000

Data Index: 965388 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.1871. Min Act: -0.0000

Data Index: 1084767 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.1536. Min Act: -0.0000

Data Index: 1354526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0642. Min Act: -0.0000

Data Index: 285800 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.1615. Min Act: -0.0000

Data Index: 1292618 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.1437. Min Act: -0.0000

Data Index: 386799 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0868. Min Act: -0.0000

Data Index: 104114 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 2.3029. Min Range: -2.3029

Max Act: 1.9595. Min Act: -0.0000

Data Index: 947221 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1112837 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0740. Min Act: -0.0000

Data Index: 244585 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0626. Min Act: -0.0000

Data Index: 1113582 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1285746 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0537. Min Act: -0.0000

Data Index: 413892 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0358. Min Act: -0.0000

Data Index: 635971 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0152. Min Act: -0.0000

Data Index: 606290 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0176. Min Act: -0.0000

Data Index: 1274726 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 2.3029. Min Range: -2.3029

Max Act: 2.0049. Min Act: -0.0000

Data Index: 146642 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 2.3029. Min Range: -2.3029

Max Act: 1.9968. Min Act: -0.0000

Data Index: 1261270 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 2.3029. Min Range: -2.3029

Max Act: 1.9896. Min Act: -0.0000

Data Index: 1296001 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 2.3029. Min Range: -2.3029

Max Act: 1.8627. Min Act: -0.0000

Data Index: 643593 (C4 (Web Text))

Max Activating Token Index: 850