Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1573117 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1512826 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1252483 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8615. Min Act: -0.0000

Data Index: 463880 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7766. Min Act: -0.0000

Data Index: 718231 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1307058 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1579355 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1238230 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7162. Min Act: -0.0000

Data Index: 589756 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8445. Min Act: -0.0000

Data Index: 319197 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7509. Min Act: -0.0000

Data Index: 446249 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6634. Min Act: -0.0000

Data Index: 168359 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7632. Min Act: -0.0000

Data Index: 54858 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1918851 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1284912 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7357. Min Act: -0.0000

Data Index: 998942 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1820892 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6804. Min Act: -0.0000

Data Index: 821379 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1429457 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1493964 (The Pile)

Max Activating Token Index: 756