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

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

Neuron 1070 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: 0.8647. Min Range: -0.8647

Max Act: 0.8647. Min Act: -0.0000

Data Index: 126599 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8025. Min Act: -0.0000

Data Index: 564447 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7825. Min Act: -0.0000

Data Index: 71358 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6714. Min Act: -0.0000

Data Index: 581354 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6088. Min Act: -0.0000

Data Index: 305458 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1095749 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6198. Min Act: -0.0000

Data Index: 320763 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6259. Min Act: -0.0000

Data Index: 625289 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7007. Min Act: -0.0000

Data Index: 507741 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6354. Min Act: -0.0000

Data Index: 844578 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6217. Min Act: -0.0000

Data Index: 450657 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5840. Min Act: -0.0000

Data Index: 686754 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5984. Min Act: -0.0000

Data Index: 673339 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6043. Min Act: -0.0000

Data Index: 604080 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5889. Min Act: -0.0000

Data Index: 370391 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5990. Min Act: -0.0000

Data Index: 841728 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5591. Min Act: -0.0000

Data Index: 668123 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5695. Min Act: -0.0000

Data Index: 859850 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5503. Min Act: -0.0000

Data Index: 66722 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.5640. Min Act: -0.0000

Data Index: 805625 (C4 (Web Text))

Max Activating Token Index: 785