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

Dataset: The Pile

Neuron 4616 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: 1.2042. Min Range: -1.2042

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1494741 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.9546. Min Act: -0.0000

Data Index: 119744 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.2042. Min Range: -1.2042

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1638906 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1638987 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1401232 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.7437. Min Act: -0.0000

Data Index: 121832 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1657647 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1015477 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6758. Min Act: -0.0000

Data Index: 178807 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1083441 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1255783 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1901941 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1415860 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1546042 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1993033 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.6109. Min Act: -0.0000

Data Index: 669412 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.5594. Min Act: 0.0000

Data Index: 389794 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.5903. Min Act: -0.0000

Data Index: 389473 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.5319. Min Act: -0.0000

Data Index: 342478 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 1.2042. Min Range: -1.2042

Max Act: 0.5772. Min Act: -0.0000

Data Index: 40318 (The Pile)

Max Activating Token Index: 74