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

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

Neuron 1091 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: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0002

Data Index: 912519 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0575. Min Act: -0.0002

Data Index: 41296 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0578. Min Act: -0.0002

Data Index: 869157 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1141783 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0516. Min Act: -0.0002

Data Index: 622083 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0541. Min Act: -0.0002

Data Index: 110202 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0539. Min Act: -0.0002

Data Index: 531277 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0496. Min Act: -0.0002

Data Index: 460624 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0512. Min Act: -0.0002

Data Index: 875514 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1610215 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0494. Min Act: -0.0002

Data Index: 771254 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0480. Min Act: -0.0002

Data Index: 919306 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0507. Min Act: -0.0002

Data Index: 110132 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0508. Min Act: -0.0002

Data Index: 348465 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1480380 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1520468 (Python Code)

Max Activating Token Index: 397

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1505939 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0483. Min Act: -0.0002

Data Index: 779484 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1232393 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1113678 (C4 (Web Text))

Max Activating Token Index: 628