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

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

Neuron 412 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0003

Data Index: 737895 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1162943 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0071. Min Act: -0.0002

Data Index: 527063 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1164371 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0068. Min Act: -0.0003

Data Index: 237183 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0070. Min Act: -0.0002

Data Index: 895552 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1009915 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1248248 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0003

Data Index: 729318 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0064. Min Act: -0.0003

Data Index: 402357 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0003

Data Index: 984078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0057. Min Act: -0.0003

Data Index: 718354 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0003

Data Index: 207325 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1359577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0058. Min Act: -0.0003

Data Index: 152520 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0060. Min Act: -0.0003

Data Index: 373363 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0003

Data Index: 476809 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0058. Min Act: -0.0002

Data Index: 349415 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0003

Data Index: 992103 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0056. Min Act: -0.0002

Data Index: 670446 (C4 (Web Text))

Max Activating Token Index: 572