Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4171. Min Range: -1.4171

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1165675 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.4171. Min Range: -1.4171

Max Act: 1.2637. Min Act: -0.0000

Data Index: 440019 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.4171. Min Range: -1.4171

Max Act: 1.2354. Min Act: -0.0001

Data Index: 836634 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9872. Min Act: -0.0000

Data Index: 704049 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1259843 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9286. Min Act: -0.0000

Data Index: 999581 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.4171. Min Range: -1.4171

Max Act: 1.1049. Min Act: -0.0000

Data Index: 211050 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9134. Min Act: -0.0000

Data Index: 9959 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1170662 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9817. Min Act: -0.0000

Data Index: 938158 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.8996. Min Act: -0.0000

Data Index: 880899 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1212480 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.8797. Min Act: -0.0000

Data Index: 11296 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1200915 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.8827. Min Act: -0.0001

Data Index: 338896 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.8569. Min Act: -0.0001

Data Index: 42306 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9111. Min Act: -0.0000

Data Index: 226093 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9063. Min Act: -0.0000

Data Index: 393697 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.8607. Min Act: -0.0001

Data Index: 722687 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.4171. Min Range: -1.4171

Max Act: 0.9002. Min Act: -0.0001

Data Index: 1078430 (C4 (Web Text))

Max Activating Token Index: 851