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

Dataset: The Pile

Neuron 255 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3733. Min Range: -5.3733

Max Act: 5.3733. Min Act: -0.0000

Data Index: 1593259 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.9495. Min Act: -0.0000

Data Index: 21038 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.5563. Min Act: -0.0000

Data Index: 1806757 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.8769. Min Act: -0.0000

Data Index: 819036 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.3651. Min Act: -0.0000

Data Index: 1316568 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 5.3733. Min Range: -5.3733

Max Act: 3.1605. Min Act: -0.0000

Data Index: 538810 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.2962. Min Act: -0.0000

Data Index: 1847446 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.4782. Min Act: -0.0000

Data Index: 293673 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.0553. Min Act: -0.0000

Data Index: 1438372 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 5.3733. Min Range: -5.3733

Max Act: 3.9849. Min Act: -0.0000

Data Index: 691887 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.1329. Min Act: -0.0000

Data Index: 1745323 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 5.3733. Min Range: -5.3733

Max Act: 3.9716. Min Act: -0.0000

Data Index: 1437537 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.4883. Min Act: -0.0000

Data Index: 649273 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.6056. Min Act: -0.0000

Data Index: 1918460 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.6515. Min Act: -0.0000

Data Index: 437146 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.2562. Min Act: -0.0000

Data Index: 1782344 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.2439. Min Act: -0.0000

Data Index: 241662 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 5.3733. Min Range: -5.3733

Max Act: 3.8715. Min Act: -0.0000

Data Index: 1584156 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.2177. Min Act: -0.0000

Data Index: 1109725 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 5.3733. Min Range: -5.3733

Max Act: 4.2040. Min Act: -0.0000

Data Index: 1828676 (The Pile)

Max Activating Token Index: 599