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

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

Neuron 2469 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: 0.5035. Min Range: -0.5035

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1409001 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1519812 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1596179 (Python Code)

Max Activating Token Index: 874

Text #3

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4035. Min Act: -0.0001

Data Index: 563086 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4332. Min Act: -0.0001

Data Index: 536850 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4210. Min Act: -0.0001

Data Index: 669461 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4259. Min Act: -0.0001

Data Index: 333784 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3946. Min Act: -0.0001

Data Index: 1196736 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3813. Min Act: -0.0001

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3547. Min Act: -0.0001

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3770. Min Act: -0.0001

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3524. Min Act: -0.0001

Data Index: 505815 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1407644 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3641. Min Act: -0.0001

Data Index: 304607 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1165529 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3689. Min Act: -0.0001

Data Index: 339817 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3574. Min Act: -0.0000

Data Index: 452578 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1385195 (Python Code)

Max Activating Token Index: 457

Text #19

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1600086 (Python Code)

Max Activating Token Index: 900