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

Dataset: The Pile

Neuron 1607 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: 0.8249. Min Range: -0.8249

Max Act: 0.7562. Min Act: -0.0000

Data Index: 640422 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1231219 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8249. Min Act: -0.0000

Data Index: 906849 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1829281 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6490. Min Act: -0.0000

Data Index: 815704 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6439. Min Act: -0.0000

Data Index: 936797 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1321615 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1270660 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1944868 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1539231 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1247282 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6416. Min Act: -0.0000

Data Index: 533782 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6430. Min Act: -0.0000

Data Index: 349036 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6570. Min Act: -0.0000

Data Index: 667110 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1068071 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1039379 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6860. Min Act: -0.0000

Data Index: 20298 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1416643 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6543. Min Act: -0.0000

Data Index: 533624 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6082. Min Act: -0.0000

Data Index: 498426 (The Pile)

Max Activating Token Index: 897