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

Dataset: The Pile

Neuron 2292 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: 3.5121. Min Range: -3.5121

Max Act: 3.2907. Min Act: -0.0000

Data Index: 1407407 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.5121. Min Act: -0.0000

Data Index: 344645 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.1702. Min Act: -0.0000

Data Index: 786369 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.1559. Min Act: -0.0000

Data Index: 159154 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.5705. Min Act: -0.0000

Data Index: 536480 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.9699. Min Act: -0.0000

Data Index: 335578 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.2065. Min Act: -0.0000

Data Index: 1002202 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.0581. Min Act: -0.0000

Data Index: 505919 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.8356. Min Act: -0.0000

Data Index: 944867 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.0147. Min Act: -0.0000

Data Index: 1675232 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.7177. Min Act: -0.0000

Data Index: 1111593 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.1426. Min Act: -0.0000

Data Index: 262208 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.0937. Min Act: -0.0000

Data Index: 260198 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.0656. Min Act: -0.0000

Data Index: 22814 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.7582. Min Act: -0.0000

Data Index: 899797 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.7235. Min Act: -0.0000

Data Index: 1774343 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.8712. Min Act: -0.0000

Data Index: 614388 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.8482. Min Act: -0.0000

Data Index: 701008 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.7306. Min Act: -0.0000

Data Index: 1071829 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 3.5121. Min Range: -3.5121

Max Act: 2.9848. Min Act: -0.0000

Data Index: 22467 (The Pile)

Max Activating Token Index: 672