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

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

Neuron 3819 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: 0.0022. Min Range: -0.0022

Max Act: 0.0020. Min Act: -0.0000

Data Index: 770500 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0022. Min Act: -0.0000

Data Index: 725574 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0020. Min Act: -0.0000

Data Index: 897873 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 353004 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0000

Data Index: 878189 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 462831 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0000

Data Index: 346464 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0017. Min Act: -0.0000

Data Index: 894636 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0016. Min Act: -0.0000

Data Index: 992430 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1460402 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1348257 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0020. Min Act: -0.0000

Data Index: 954997 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0021. Min Act: -0.0000

Data Index: 44339 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1189036 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0017. Min Act: -0.0000

Data Index: 195769 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1126683 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1375210 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 925519 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0000

Data Index: 130006 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0000

Data Index: 35826 (C4 (Web Text))

Max Activating Token Index: 268