Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9395. Min Act: -0.0000

Data Index: 876567 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1495411 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9458. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1221982 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1081225 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8391. Min Act: -0.0000

Data Index: 377776 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8060. Min Act: -0.0000

Data Index: 193791 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1685234 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1181 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7368. Min Act: -0.0000

Data Index: 532226 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1834626 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1755628 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1376508 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1612692 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7684. Min Act: -0.0000

Data Index: 649186 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1574271 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1864940 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7319. Min Act: -0.0000

Data Index: 150779 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1656101 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6879. Min Act: -0.0000

Data Index: 25456 (The Pile)

Max Activating Token Index: 900