Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1233 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0002

Data Index: 649172 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0659. Min Act: -0.0002

Data Index: 453093 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0664. Min Act: -0.0002

Data Index: 362131 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1226606 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0659. Min Act: -0.0002

Data Index: 429469 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0676. Min Act: -0.0002

Data Index: 270592 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1087361 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0624. Min Act: -0.0002

Data Index: 388906 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0587. Min Act: -0.0002

Data Index: 510769 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0590. Min Act: -0.0002

Data Index: 450104 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1027369 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0588. Min Act: -0.0002

Data Index: 589985 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0562. Min Act: -0.0002

Data Index: 554135 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0585. Min Act: -0.0002

Data Index: 185499 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0570. Min Act: -0.0002

Data Index: 602686 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0577. Min Act: -0.0001

Data Index: 631768 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0615. Min Act: -0.0002

Data Index: 9552 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0569. Min Act: -0.0002

Data Index: 956537 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0560. Min Act: -0.0002

Data Index: 415202 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0563. Min Act: -0.0002

Data Index: 692609 (C4 (Web Text))

Max Activating Token Index: 792