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

Dataset: The Pile

Neuron 3419 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: 1.2169. Min Range: -1.2169

Max Act: 1.2169. Min Act: -0.0000

Data Index: 660976 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1025556 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1277156 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1567133 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1633905 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0742. Min Act: -0.0000

Data Index: 788292 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9866. Min Act: -0.0000

Data Index: 373718 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9733. Min Act: -0.0000

Data Index: 6132 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0531. Min Act: -0.0000

Data Index: 764984 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1244447 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1777615 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1193942 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1346698 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9330. Min Act: -0.0000

Data Index: 491026 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9736. Min Act: -0.0000

Data Index: 592480 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1026420 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9312. Min Act: -0.0000

Data Index: 381479 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1614834 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1165566 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.2169. Min Range: -1.2169

Max Act: 0.9697. Min Act: -0.0000

Data Index: 685362 (The Pile)

Max Activating Token Index: 443