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

Dataset: The Pile

Neuron 718 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: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0000

Data Index: 152716 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3474. Min Act: -0.0000

Data Index: 737788 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3603. Min Act: -0.0000

Data Index: 655463 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1256117 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1677849 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1456740 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1562864 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2728. Min Act: -0.0000

Data Index: 83803 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2694. Min Act: -0.0000

Data Index: 987940 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2743. Min Act: -0.0000

Data Index: 558132 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1899578 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1924446 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1092788 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1526524 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1962433 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1231395 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2327. Min Act: -0.0000

Data Index: 828274 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1367849 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2287. Min Act: -0.0000

Data Index: 475696 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1802808 (The Pile)

Max Activating Token Index: 86