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

Dataset: The Pile

Neuron 2247 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.3801. Min Act: -0.0000

Data Index: 400095 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1666320 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1418099 (The Pile)

Max Activating Token Index: 474

Text #3

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1763027 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.9982. Min Act: -0.0000

Data Index: 64315 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.0217. Min Act: -0.0000

Data Index: 419426 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 1.3847. Min Range: -1.3847

Max Act: 1.0493. Min Act: -0.0000

Data Index: 389307 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1536729 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8767. Min Act: -0.0000

Data Index: 625747 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1704787 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1253435 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8367. Min Act: -0.0000

Data Index: 27775 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1832688 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.7456. Min Act: -0.0000

Data Index: 183235 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.7511. Min Act: -0.0000

Data Index: 155881 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1945330 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.7208. Min Act: -0.0000

Data Index: 912966 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1388551 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1261750 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 1.3847. Min Range: -1.3847

Max Act: 0.7746. Min Act: -0.0000

Data Index: 333853 (The Pile)

Max Activating Token Index: 231