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

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

Neuron 586 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: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0006

Data Index: 739542 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0702. Min Act: -0.0006

Data Index: 1387635 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1388621 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0621. Min Act: -0.0006

Data Index: 1635754 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0652. Min Act: -0.0006

Data Index: 481002 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0604. Min Act: -0.0006

Data Index: 1601071 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1610187 (Python Code)

Max Activating Token Index: 616

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1375652 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0569. Min Act: -0.0006

Data Index: 739849 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0575. Min Act: -0.0006

Data Index: 237736 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0573. Min Act: -0.0006

Data Index: 555510 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0574. Min Act: -0.0006

Data Index: 1187449 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0557. Min Act: -0.0006

Data Index: 640849 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0556. Min Act: -0.0006

Data Index: 275708 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0579. Min Act: -0.0006

Data Index: 882923 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1251181 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0552. Min Act: -0.0006

Data Index: 581470 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0552. Min Act: -0.0006

Data Index: 39983 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0540. Min Act: -0.0006

Data Index: 559657 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0540. Min Act: -0.0006

Data Index: 1060475 (C4 (Web Text))

Max Activating Token Index: 420