Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 663942 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0837. Min Act: -0.0001

Data Index: 973788 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0806. Min Act: -0.0000

Data Index: 471184 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1644194 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1532232 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1479068 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1007526 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1495340 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0682. Min Act: -0.0001

Data Index: 56883 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0681. Min Act: -0.0001

Data Index: 702158 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1521015 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1111371 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0634. Min Act: -0.0001

Data Index: 545240 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1225718 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0657. Min Act: -0.0000

Data Index: 212587 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0625. Min Act: -0.0000

Data Index: 80500 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1206288 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0625. Min Act: -0.0001

Data Index: 400055 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0648. Min Act: -0.0000

Data Index: 277227 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0645. Min Act: -0.0001

Data Index: 572879 (C4 (Web Text))

Max Activating Token Index: 367