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

Dataset: The Pile

Neuron 357 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3836. Min Act: -0.0000

Data Index: 934813 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1007798 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.4012. Min Act: -0.0000

Data Index: 48797 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1319863 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3236. Min Act: -0.0000

Data Index: 367111 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3175. Min Act: -0.0000

Data Index: 898474 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1773898 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2918. Min Act: -0.0000

Data Index: 297237 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1090475 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1324279 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2747. Min Act: -0.0000

Data Index: 891295 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2575. Min Act: -0.0000

Data Index: 683932 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2796. Min Act: -0.0000

Data Index: 652236 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2542. Min Act: -0.0000

Data Index: 292500 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2702. Min Act: -0.0000

Data Index: 833939 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1967878 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2508. Min Act: -0.0000

Data Index: 240548 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2606. Min Act: -0.0000

Data Index: 431171 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2788. Min Act: -0.0000

Data Index: 857210 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2692. Min Act: -0.0000

Data Index: 162952 (The Pile)

Max Activating Token Index: 200