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

Dataset: The Pile

Neuron 2252 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1725519 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.5606. Min Act: -0.0000

Data Index: 821617 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.6080. Min Act: -0.0000

Data Index: 618606 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1788377 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.5624. Min Act: -0.0000

Data Index: 467155 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1825657 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1942325 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1192580 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1509140 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.4053. Min Act: -0.0000

Data Index: 621924 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1489263 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1274504 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1446932 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.3228. Min Act: -0.0000

Data Index: 607951 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1844877 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1046696 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1962280 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1387058 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.2534. Min Act: -0.0000

Data Index: 679740 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.1743. Min Act: -0.0000

Data Index: 216913 (The Pile)

Max Activating Token Index: 661