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

Dataset: The Pile

Neuron 4008 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.3502. Min Act: -0.0000

Data Index: 968893 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.3706. Min Act: -0.0000

Data Index: 678361 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.4211. Min Act: -0.0000

Data Index: 235084 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1745379 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1984056 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2919. Min Act: -0.0000

Data Index: 223984 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2842. Min Act: -0.0000

Data Index: 838820 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2711. Min Act: -0.0000

Data Index: 36650 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1858. Min Act: -0.0000

Data Index: 388135 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2382. Min Act: -0.0000

Data Index: 183662 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1597913 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1076591 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1271. Min Act: -0.0000

Data Index: 168507 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1529500 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1391883 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1598142 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.0286. Min Act: -0.0000

Data Index: 303333 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1256023 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.1601. Min Act: -0.0000

Data Index: 103961 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 1.4211. Min Range: -1.4211

Max Act: 1.2023. Min Act: -0.0000

Data Index: 994304 (The Pile)

Max Activating Token Index: 931