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

Dataset: The Pile

Neuron 1572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7809. Min Act: -0.0000

Data Index: 93485 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4687. Min Act: -0.0000

Data Index: 792257 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4602. Min Act: -0.0000

Data Index: 872062 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4275. Min Act: -0.0000

Data Index: 859862 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4189. Min Act: -0.0000

Data Index: 298399 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1299773 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1072604 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3929. Min Act: -0.0000

Data Index: 716827 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3908. Min Act: -0.0000

Data Index: 157312 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4014. Min Act: -0.0000

Data Index: 40994 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1568535 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3859. Min Act: -0.0000

Data Index: 57403 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3824. Min Act: -0.0000

Data Index: 15605 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1024403 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1018943 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3507. Min Act: -0.0000

Data Index: 765946 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3610. Min Act: -0.0000

Data Index: 652675 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3809. Min Act: -0.0000

Data Index: 777326 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1581420 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.3577. Min Act: -0.0000

Data Index: 125541 (The Pile)

Max Activating Token Index: 848