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

Dataset: The Pile

Neuron 4226 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: 3.5357. Min Range: -3.5357

Max Act: 3.5357. Min Act: -0.0000

Data Index: 1829384 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.5708. Min Act: -0.0000

Data Index: 826341 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.3999. Min Act: -0.0000

Data Index: 168422 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.4385. Min Act: -0.0000

Data Index: 1365413 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.9406. Min Act: -0.0000

Data Index: 1395821 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.1096. Min Act: -0.0000

Data Index: 432234 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.0858. Min Act: -0.0000

Data Index: 1670769 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.1574. Min Act: -0.0000

Data Index: 1183847 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.1253. Min Act: -0.0000

Data Index: 125724 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.9990. Min Act: -0.0000

Data Index: 1175656 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.9432. Min Act: -0.0000

Data Index: 116639 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 3.5357. Min Range: -3.5357

Max Act: 2.2216. Min Act: -0.0000

Data Index: 1867885 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.7945. Min Act: -0.0000

Data Index: 1348540 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.9529. Min Act: -0.0000

Data Index: 1250164 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1378296 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.9335. Min Act: -0.0000

Data Index: 531134 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.6383. Min Act: -0.0000

Data Index: 841057 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1861405 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1856532 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 3.5357. Min Range: -3.5357

Max Act: 1.8405. Min Act: -0.0000

Data Index: 131168 (The Pile)

Max Activating Token Index: 520