Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0001

Data Index: 246499 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0744. Min Act: -0.0001

Data Index: 492453 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0713. Min Act: -0.0001

Data Index: 109548 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0682. Min Act: -0.0001

Data Index: 76217 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0661. Min Act: -0.0002

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1024868 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0519. Min Act: -0.0001

Data Index: 106048 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0628. Min Act: -0.0001

Data Index: 345138 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0504. Min Act: -0.0001

Data Index: 810705 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0602. Min Act: -0.0001

Data Index: 611713 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1219017 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1276282 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0552. Min Act: -0.0001

Data Index: 440364 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0614. Min Act: -0.0001

Data Index: 596133 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1098575 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0611. Min Act: -0.0001

Data Index: 659160 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0576. Min Act: -0.0001

Data Index: 94265 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1024568 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1104774 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0591. Min Act: -0.0001

Data Index: 18910 (C4 (Web Text))

Max Activating Token Index: 8