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

Dataset: The Pile

Neuron 927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1298068 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1514695 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.2260. Min Act: -0.0000

Data Index: 726607 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0864. Min Act: -0.0000

Data Index: 142252 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0778. Min Act: -0.0000

Data Index: 967395 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1136025 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.1070. Min Act: -0.0000

Data Index: 470232 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1401524 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1526859 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0511. Min Act: -0.0000

Data Index: 77068 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1125350 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 1.3781. Min Range: -1.3781

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1849558 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1857372 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1414592 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1686571 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8787. Min Act: -0.0000

Data Index: 773990 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.8849. Min Act: -0.0000

Data Index: 541276 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9185. Min Act: -0.0000

Data Index: 672524 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9592. Min Act: -0.0000

Data Index: 463697 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.3781. Min Range: -1.3781

Max Act: 0.9703. Min Act: -0.0000

Data Index: 91937 (The Pile)

Max Activating Token Index: 656