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

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

Neuron 1161 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.9474. Min Act: -0.0000

Data Index: 751181 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.9544. Min Act: -0.0000

Data Index: 765563 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.9051. Min Act: -0.0000

Data Index: 525543 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8675. Min Act: 0.0003

Data Index: 1005134 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8412. Min Act: -0.0000

Data Index: 955046 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8029. Min Act: -0.0000

Data Index: 883349 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8118. Min Act: -0.0000

Data Index: 505977 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8137. Min Act: -0.0000

Data Index: 439846 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.8138. Min Act: 0.0003

Data Index: 1032636 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7732. Min Act: -0.0000

Data Index: 478304 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7678. Min Act: 0.0000

Data Index: 1289043 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1072358 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7053. Min Act: -0.0000

Data Index: 646990 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7056. Min Act: -0.0000

Data Index: 524852 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7136. Min Act: -0.0000

Data Index: 427763 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1229140 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7204. Min Act: -0.0000

Data Index: 26992 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1118241 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1035395 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.9544. Min Range: -0.9544

Max Act: 0.7114. Min Act: 0.0003

Data Index: 377710 (C4 (Web Text))

Max Activating Token Index: 937