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

Dataset: The Pile

Neuron 4319 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: 0.2206. Min Range: -0.2206

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1652606 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1233620 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1770367 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1099441 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1737148 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1733912 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1749075 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1376829 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1946369 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1588983 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1562. Min Act: -0.0000

Data Index: 303436 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1893596 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1534. Min Act: -0.0000

Data Index: 609494 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1523. Min Act: -0.0000

Data Index: 730893 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1026215 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1487872 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1591. Min Act: -0.0000

Data Index: 977325 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1734859 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1508. Min Act: -0.0000

Data Index: 444158 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1517. Min Act: -0.0000

Data Index: 721878 (The Pile)

Max Activating Token Index: 705