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

Dataset: The Pile

Neuron 3164 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: 1.1215. Min Range: -1.1215

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1463222 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.1215. Min Range: -1.1215

Max Act: 1.0805. Min Act: -0.0000

Data Index: 269370 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1008424 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.1215. Min Range: -1.1215

Max Act: 1.0675. Min Act: -0.0000

Data Index: 49184 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1613834 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 1.1215. Min Range: -1.1215

Max Act: 1.0618. Min Act: -0.0000

Data Index: 369366 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 1.1215. Min Range: -1.1215

Max Act: 1.0338. Min Act: -0.0000

Data Index: 529325 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 1.1215. Min Range: -1.1215

Max Act: 1.0281. Min Act: -0.0001

Data Index: 1518202 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1047899 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9596. Min Act: -0.0000

Data Index: 737159 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9162. Min Act: -0.0000

Data Index: 143519 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9044. Min Act: -0.0000

Data Index: 924314 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.8971. Min Act: -0.0001

Data Index: 508827 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9252. Min Act: -0.0000

Data Index: 393418 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.8712. Min Act: -0.0000

Data Index: 338203 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9199. Min Act: -0.0000

Data Index: 114143 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.9106. Min Act: -0.0000

Data Index: 961851 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1075927 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1468899 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 1.1215. Min Range: -1.1215

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1200940 (The Pile)

Max Activating Token Index: 195