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

Dataset: The Pile

Neuron 753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1401463 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0458. Min Act: -0.0000

Data Index: 78117 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1497426 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1444823 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1537583 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8374. Min Act: -0.0000

Data Index: 707207 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8986. Min Act: -0.0000

Data Index: 676435 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1943581 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8293. Min Act: -0.0000

Data Index: 566792 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8696. Min Act: -0.0000

Data Index: 851790 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1540048 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8430. Min Act: -0.0000

Data Index: 148869 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7421. Min Act: -0.0000

Data Index: 455862 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1578040 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1152675 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8070. Min Act: -0.0000

Data Index: 475457 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8379. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1275403 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1613711 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1526067 (The Pile)

Max Activating Token Index: 203