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

Dataset: The Pile

Neuron 2052 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: 1.7802. Min Range: -1.7802

Max Act: 1.7802. Min Act: -0.0000

Data Index: 507921 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4126. Min Act: -0.0000

Data Index: 852182 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6377. Min Act: -0.0000

Data Index: 296837 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1582625 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5903. Min Act: -0.0000

Data Index: 799380 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4903. Min Act: -0.0000

Data Index: 76241 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1455244 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1954935 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1816341 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6399. Min Act: -0.0000

Data Index: 1733573 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1155991 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1888744 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 1.7802. Min Range: -1.7802

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1550293 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4771. Min Act: -0.0000

Data Index: 1496889 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.3334. Min Act: -0.0000

Data Index: 795854 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4805. Min Act: -0.0000

Data Index: 186454 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1783994 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1291322 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1027311 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1375848 (The Pile)

Max Activating Token Index: 432