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

Dataset: The Pile

Neuron 1443 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: 0.3160. Min Range: -0.3160

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1789859 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1030436 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3084. Min Act: -0.0000

Data Index: 567245 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1524678 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3036. Min Act: -0.0000

Data Index: 96290 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1365503 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2983. Min Act: -0.0000

Data Index: 53814 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2804. Min Act: -0.0000

Data Index: 464950 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2726. Min Act: -0.0000

Data Index: 511496 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1734580 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1259324 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1203656 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1871423 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2506. Min Act: -0.0000

Data Index: 217789 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2814. Min Act: -0.0000

Data Index: 962797 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1969905 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1349398 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2510. Min Act: -0.0000

Data Index: 106047 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1230496 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1106754 (The Pile)

Max Activating Token Index: 126