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

Dataset: The Pile

Neuron 4326 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: 1.1342. Min Range: -1.1342

Max Act: 1.1218. Min Act: -0.0000

Data Index: 265574 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.1342. Min Range: -1.1342

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1313079 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.1342. Min Range: -1.1342

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1556502 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1712093 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1561350 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1662969 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9662. Min Act: -0.0000

Data Index: 743723 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9314. Min Act: -0.0000

Data Index: 892662 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8706. Min Act: -0.0000

Data Index: 836396 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1268097 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1427360 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1683317 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1045927 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9039. Min Act: -0.0000

Data Index: 742706 (The Pile)

Max Activating Token Index: 50

Text #14

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9176. Min Act: -0.0000

Data Index: 166583 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8623. Min Act: -0.0000

Data Index: 935665 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8077. Min Act: -0.0000

Data Index: 424456 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8505. Min Act: -0.0000

Data Index: 605350 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8340. Min Act: -0.0000

Data Index: 85269 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.9519. Min Act: -0.0000

Data Index: 215426 (The Pile)

Max Activating Token Index: 197