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

Dataset: The Pile

Neuron 4744 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0757. Min Range: -8.0757

Max Act: 8.0757. Min Act: -0.0000

Data Index: 295255 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 8.0757. Min Range: -8.0757

Max Act: 6.2191. Min Act: -0.0000

Data Index: 1284584 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.8195. Min Act: -0.0000

Data Index: 2550 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 8.0757. Min Range: -8.0757

Max Act: 6.2443. Min Act: -0.0000

Data Index: 1559013 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.6649. Min Act: -0.0000

Data Index: 855172 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.1812. Min Act: -0.0000

Data Index: 1796821 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.0476. Min Act: -0.0000

Data Index: 1679622 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.5465. Min Act: -0.0000

Data Index: 176184 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.8291. Min Act: -0.0000

Data Index: 1048749 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.7726. Min Act: -0.0000

Data Index: 1634826 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.6257. Min Act: -0.0000

Data Index: 1259427 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.1255. Min Act: -0.0000

Data Index: 1983661 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.9581. Min Act: -0.0000

Data Index: 1253586 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.7906. Min Act: -0.0000

Data Index: 909577 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 8.0757. Min Range: -8.0757

Max Act: 5.6083. Min Act: -0.0000

Data Index: 1400162 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 8.0757. Min Range: -8.0757

Max Act: 6.3596. Min Act: -0.0000

Data Index: 1492302 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.1472. Min Act: -0.0000

Data Index: 1635522 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.1503. Min Act: -0.0000

Data Index: 290072 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 8.0757. Min Range: -8.0757

Max Act: 4.6600. Min Act: -0.0000

Data Index: 1938985 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 8.0757. Min Range: -8.0757

Max Act: 3.6566. Min Act: -0.0000

Data Index: 1125147 (The Pile)

Max Activating Token Index: 239