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

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

Neuron 4658 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0677. Min Act: -0.0002

Data Index: 437950 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 10470 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0002

Data Index: 821211 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0621. Min Act: -0.0002

Data Index: 901719 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1296112 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0621. Min Act: -0.0002

Data Index: 555207 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1145658 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1127080 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0575. Min Act: -0.0002

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0552. Min Act: -0.0002

Data Index: 789032 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0530. Min Act: -0.0002

Data Index: 254419 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0617. Min Act: -0.0002

Data Index: 742348 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0577. Min Act: -0.0002

Data Index: 429735 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0530. Min Act: -0.0002

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0002

Data Index: 474060 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0538. Min Act: -0.0002

Data Index: 699108 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0560. Min Act: -0.0002

Data Index: 258714 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0535. Min Act: -0.0002

Data Index: 680400 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1132549 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0478. Min Act: -0.0002

Data Index: 160531 (C4 (Web Text))

Max Activating Token Index: 708