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

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

Neuron 4585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1601910 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1347153 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1607345 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1372361 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1040815 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0558. Min Act: -0.0003

Data Index: 316638 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1040297 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1445590 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0523. Min Act: -0.0003

Data Index: 8014 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1597273 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0506. Min Act: -0.0003

Data Index: 915821 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1109214 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1421521 (Python Code)

Max Activating Token Index: 211

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1592123 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1040438 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0474. Min Act: -0.0003

Data Index: 78427 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0501. Min Act: -0.0003

Data Index: 359750 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1116600 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1376709 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1440907 (Python Code)

Max Activating Token Index: 59