Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1753 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1213853 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0937. Min Act: -0.0002

Data Index: 833431 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0824. Min Act: -0.0002

Data Index: 576027 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1250470 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1119245 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0688. Min Act: -0.0002

Data Index: 637815 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0654. Min Act: -0.0001

Data Index: 213132 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1240827 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0630. Min Act: -0.0002

Data Index: 324898 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0562. Min Act: -0.0002

Data Index: 448358 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0611. Min Act: -0.0002

Data Index: 721330 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0566. Min Act: -0.0002

Data Index: 844090 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0594. Min Act: -0.0002

Data Index: 984101 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0561. Min Act: -0.0002

Data Index: 446319 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0555. Min Act: -0.0002

Data Index: 53644 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1211716 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0524. Min Act: -0.0002

Data Index: 188148 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0527. Min Act: -0.0002

Data Index: 110502 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1559430 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0538. Min Act: -0.0002

Data Index: 620411 (C4 (Web Text))

Max Activating Token Index: 784