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

Dataset: The Pile

Neuron 1756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.9497. Min Act: -0.0000

Data Index: 179892 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1128. Min Act: -0.0000

Data Index: 1903973 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.0154. Min Act: -0.0000

Data Index: 1404137 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.6990. Min Act: -0.0000

Data Index: 1176614 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.3914. Min Act: -0.0000

Data Index: 1976600 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.0842. Min Act: -0.0000

Data Index: 731715 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.6052. Min Act: -0.0000

Data Index: 369420 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.5638. Min Act: -0.0000

Data Index: 200724 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.3142. Min Act: -0.0000

Data Index: 324301 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.8256. Min Act: -0.0000

Data Index: 1777510 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.4073. Min Act: -0.0000

Data Index: 933942 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 3.9497. Min Range: -3.9497

Max Act: 1.8760. Min Act: -0.0000

Data Index: 830954 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.7451. Min Act: -0.0000

Data Index: 1039783 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.2667. Min Act: -0.0000

Data Index: 1975846 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.3353. Min Act: -0.0000

Data Index: 589690 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.2579. Min Act: -0.0000

Data Index: 1192664 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.1684. Min Act: -0.0000

Data Index: 1320669 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.0833. Min Act: -0.0000

Data Index: 914473 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1871255 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 3.9497. Min Range: -3.9497

Max Act: 1.7192. Min Act: -0.0000

Data Index: 819839 (The Pile)

Max Activating Token Index: 600