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

Dataset: The Pile

Neuron 366 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: 1.1649. Min Range: -1.1649

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1766804 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 1.1649. Min Range: -1.1649

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1154616 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1453040 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1541434 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1780702 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1042347 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9290. Min Act: -0.0000

Data Index: 72320 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1411520 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1615606 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1645770 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8859. Min Act: -0.0000

Data Index: 441463 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1343490 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9365. Min Act: -0.0000

Data Index: 886690 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1656981 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1783425 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8994. Min Act: -0.0000

Data Index: 403756 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8636. Min Act: -0.0000

Data Index: 954094 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8655. Min Act: -0.0000

Data Index: 948396 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1619652 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.1649. Min Range: -1.1649

Max Act: 0.8586. Min Act: -0.0000

Data Index: 11752 (The Pile)

Max Activating Token Index: 748