Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1697. Min Act: -0.0000

Data Index: 154983 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1937019 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0269. Min Act: -0.0000

Data Index: 480941 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1299880 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0646. Min Act: -0.0000

Data Index: 436219 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1705776 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9776. Min Act: -0.0000

Data Index: 358438 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9274. Min Act: -0.0000

Data Index: 449234 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1272310 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9341. Min Act: -0.0000

Data Index: 844792 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1607. Min Act: -0.0000

Data Index: 807125 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9489. Min Act: -0.0000

Data Index: 979538 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1559815 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9908. Min Act: -0.0000

Data Index: 556209 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1533376 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9733. Min Act: -0.0000

Data Index: 811709 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1707923 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1699800 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9246. Min Act: -0.0000

Data Index: 396749 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8896. Min Act: -0.0000

Data Index: 143463 (The Pile)

Max Activating Token Index: 244