Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 331 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0006

Data Index: 402547 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0559. Min Act: -0.0005

Data Index: 790066 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0534. Min Act: -0.0006

Data Index: 527322 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0502. Min Act: -0.0006

Data Index: 647591 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1352146 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0494. Min Act: -0.0006

Data Index: 1011370 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0480. Min Act: -0.0006

Data Index: 441154 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0475. Min Act: -0.0006

Data Index: 562270 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1089364 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0439. Min Act: -0.0006

Data Index: 36077 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0467. Min Act: -0.0006

Data Index: 701637 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0466. Min Act: -0.0006

Data Index: 127593 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0465. Min Act: -0.0006

Data Index: 212293 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0464. Min Act: -0.0006

Data Index: 635521 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0464. Min Act: -0.0006

Data Index: 545080 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0464. Min Act: -0.0006

Data Index: 40227 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0441. Min Act: -0.0006

Data Index: 333686 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0461. Min Act: -0.0006

Data Index: 934573 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0455. Min Act: -0.0006

Data Index: 528072 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1012640 (C4 (Web Text))

Max Activating Token Index: 439