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

Dataset: The Pile

Neuron 22 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: 0.9774. Min Range: -0.9774

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1523060 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1351879 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7301. Min Act: -0.0000

Data Index: 944576 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8453. Min Act: -0.0000

Data Index: 719888 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8021. Min Act: -0.0000

Data Index: 172351 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7224. Min Act: -0.0000

Data Index: 378160 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1660029 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7396. Min Act: -0.0000

Data Index: 272856 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1062805 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7807. Min Act: -0.0000

Data Index: 227106 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7478. Min Act: -0.0000

Data Index: 979281 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1691266 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7114. Min Act: -0.0000

Data Index: 993314 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1593704 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6395. Min Act: -0.0000

Data Index: 60723 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1587251 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1227318 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7631. Min Act: -0.0000

Data Index: 231144 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.6539. Min Act: -0.0000

Data Index: 582480 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.9774. Min Range: -0.9774

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1683523 (The Pile)

Max Activating Token Index: 206