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

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

Neuron 3267 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: 0.0729. Min Range: -0.0729

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1259726 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1320571 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1205541 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0646. Min Act: -0.0002

Data Index: 547615 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1332582 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0658. Min Act: -0.0002

Data Index: 847633 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0579. Min Act: -0.0002

Data Index: 187513 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0553. Min Act: -0.0002

Data Index: 634649 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0613. Min Act: -0.0002

Data Index: 115229 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1276706 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0559. Min Act: -0.0002

Data Index: 673924 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0470. Min Act: -0.0002

Data Index: 700541 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1191749 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0558. Min Act: -0.0002

Data Index: 187187 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0492. Min Act: -0.0002

Data Index: 884586 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0554. Min Act: -0.0002

Data Index: 424489 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0488. Min Act: -0.0002

Data Index: 272301 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0486. Min Act: -0.0002

Data Index: 655873 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0522. Min Act: -0.0002

Data Index: 661798 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1168040 (C4 (Web Text))

Max Activating Token Index: 269