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

Dataset: The Pile

Neuron 3148 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: 0.3715. Min Range: -0.3715

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1895522 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1890072 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1545737 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1299331 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2792. Min Act: -0.0000

Data Index: 513882 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1046831 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1226487 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1339904 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1091594 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1407433 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1152000 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2633. Min Act: -0.0000

Data Index: 635356 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1624281 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2580. Min Act: -0.0000

Data Index: 313180 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1791237 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1977039 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1434672 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2573. Min Act: -0.0000

Data Index: 842265 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1007779 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2389. Min Act: -0.0000

Data Index: 817132 (The Pile)

Max Activating Token Index: 631