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

Dataset: The Pile

Neuron 5079 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: 1.5616. Min Range: -1.5616

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1684262 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3738. Min Act: -0.0000

Data Index: 1223658 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3464. Min Act: -0.0000

Data Index: 866684 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3194. Min Act: -0.0000

Data Index: 892025 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1892782 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1474757 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3014. Min Act: -0.0000

Data Index: 300240 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1188517 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1601075 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.3223. Min Act: -0.0000

Data Index: 435851 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1799203 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2339. Min Act: -0.0000

Data Index: 543116 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2712. Min Act: -0.0000

Data Index: 1380604 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1071784 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1825283 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1161081 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1434183 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2239. Min Act: -0.0000

Data Index: 144353 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.1255. Min Act: -0.0000

Data Index: 242505 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1208644 (The Pile)

Max Activating Token Index: 664