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

Dataset: The Pile

Neuron 4674 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1413323 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.4475. Min Act: -0.0000

Data Index: 1527874 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1139564 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.0560. Min Act: -0.0000

Data Index: 1183075 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.8982. Min Act: -0.0000

Data Index: 448200 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.0903. Min Act: -0.0000

Data Index: 1645772 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6714. Min Act: -0.0000

Data Index: 782359 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.9501. Min Act: -0.0000

Data Index: 307314 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.0835. Min Act: -0.0000

Data Index: 1985653 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 3.4475. Min Range: -3.4475

Max Act: 3.2589. Min Act: -0.0000

Data Index: 215516 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.7407. Min Act: -0.0000

Data Index: 27792 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6601. Min Act: -0.0000

Data Index: 635579 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.3710. Min Act: -0.0000

Data Index: 414105 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.6807. Min Act: -0.0000

Data Index: 262903 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.3021. Min Act: -0.0000

Data Index: 353062 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.2770. Min Act: -0.0000

Data Index: 1867357 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.5911. Min Act: -0.0000

Data Index: 445457 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.8048. Min Act: -0.0000

Data Index: 553545 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.5553. Min Act: -0.0000

Data Index: 1119714 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 3.4475. Min Range: -3.4475

Max Act: 2.5220. Min Act: -0.0000

Data Index: 1713862 (The Pile)

Max Activating Token Index: 185