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

Dataset: The Pile

Neuron 305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.4368. Min Act: -0.0000

Data Index: 232211 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.1527. Min Act: -0.0000

Data Index: 357542 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.1730. Min Act: -0.0000

Data Index: 548925 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2100. Min Act: -0.0000

Data Index: 456419 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0679. Min Act: -0.0000

Data Index: 585357 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.2115. Min Act: -0.0000

Data Index: 992802 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1731724 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1377251 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0288. Min Act: -0.0000

Data Index: 377538 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0313. Min Act: -0.0000

Data Index: 560862 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9763. Min Act: -0.0000

Data Index: 594276 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0536. Min Act: -0.0000

Data Index: 101851 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1449375 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9813. Min Act: -0.0000

Data Index: 274774 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.8932. Min Act: -0.0000

Data Index: 235330 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1313599 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9529. Min Act: -0.0000

Data Index: 193974 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1545505 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.4368. Min Range: -1.4368

Max Act: 1.0246. Min Act: -0.0000

Data Index: 820920 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 1.4368. Min Range: -1.4368

Max Act: 0.8985. Min Act: -0.0000

Data Index: 929434 (The Pile)

Max Activating Token Index: 959