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

Dataset: The Pile

Neuron 5088 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: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1424477 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6170. Min Act: -0.0000

Data Index: 545957 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5865. Min Act: -0.0000

Data Index: 607936 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5505. Min Act: -0.0000

Data Index: 618131 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5269. Min Act: -0.0000

Data Index: 318063 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4858. Min Act: -0.0000

Data Index: 52095 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4888. Min Act: -0.0000

Data Index: 987762 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4742. Min Act: -0.0000

Data Index: 5541 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4984. Min Act: -0.0000

Data Index: 288687 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1391424 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4156. Min Act: -0.0000

Data Index: 614239 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1607700 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1174384 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.3376. Min Act: -0.0000

Data Index: 215751 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1431589 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4590. Min Act: -0.0000

Data Index: 220491 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4577. Min Act: -0.0000

Data Index: 665178 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1379774 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4171. Min Act: -0.0000

Data Index: 989943 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1590129 (The Pile)

Max Activating Token Index: 742