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

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

Neuron 1743 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: 1.0596. Min Range: -1.0596

Max Act: 1.0596. Min Act: -0.0000

Data Index: 141643 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9081. Min Act: -0.0000

Data Index: 791991 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8075. Min Act: -0.0000

Data Index: 282253 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7155. Min Act: -0.0000

Data Index: 404849 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6695. Min Act: -0.0000

Data Index: 145716 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6747. Min Act: -0.0000

Data Index: 480443 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1341386 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6098. Min Act: -0.0000

Data Index: 326298 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6054. Min Act: -0.0000

Data Index: 902031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1230099 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5963. Min Act: -0.0000

Data Index: 275386 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5370. Min Act: -0.0000

Data Index: 854728 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1606386 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5048. Min Act: -0.0000

Data Index: 356412 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5348. Min Act: -0.0000

Data Index: 550906 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5143. Min Act: -0.0000

Data Index: 917844 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1289028 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.4760. Min Act: 0.0000

Data Index: 963514 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5182. Min Act: -0.0000

Data Index: 541879 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.4831. Min Act: -0.0000

Data Index: 985561 (C4 (Web Text))

Max Activating Token Index: 630