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

Dataset: The Pile

Neuron 4860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1515744 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.6398. Min Act: -0.0000

Data Index: 29017 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5380. Min Act: -0.0000

Data Index: 523265 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1159028 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1343630 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1512209 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1210620 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1436615 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4778. Min Act: -0.0000

Data Index: 646009 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1403180 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4858. Min Act: -0.0000

Data Index: 69576 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4525. Min Act: -0.0000

Data Index: 21566 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4912. Min Act: -0.0000

Data Index: 6217 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4622. Min Act: -0.0000

Data Index: 493837 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1401054 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4281. Min Act: -0.0000

Data Index: 821661 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1660763 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4384. Min Act: -0.0000

Data Index: 395438 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1645207 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4297. Min Act: -0.0000

Data Index: 424591 (The Pile)

Max Activating Token Index: 933