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

Dataset: The Pile

Neuron 1986 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5345. Min Act: -0.0000

Data Index: 275876 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.2772. Min Act: -0.0000

Data Index: 518810 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1493567 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.2421. Min Act: -0.0000

Data Index: 821940 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0870. Min Act: -0.0000

Data Index: 214422 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.1750. Min Act: -0.0000

Data Index: 602828 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1712408 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0697. Min Act: -0.0000

Data Index: 523805 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1781663 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0548. Min Act: -0.0000

Data Index: 973739 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.1114. Min Act: -0.0000

Data Index: 913552 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1428388 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0305. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9959. Min Act: -0.0000

Data Index: 627932 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1033664 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9536. Min Act: -0.0000

Data Index: 643273 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9862. Min Act: -0.0000

Data Index: 255297 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1152475 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9806. Min Act: -0.0000

Data Index: 71810 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8199. Min Act: -0.0000

Data Index: 93790 (The Pile)

Max Activating Token Index: 967