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

Dataset: The Pile

Neuron 2262 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: 0.4519. Min Range: -0.4519

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1844899 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1223254 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3780. Min Act: -0.0000

Data Index: 752679 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1814163 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3636. Min Act: -0.0000

Data Index: 705786 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1034361 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3065. Min Act: 0.0000

Data Index: 821672 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1138365 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1767092 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3370. Min Act: -0.0000

Data Index: 456650 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3645. Min Act: 0.0000

Data Index: 1346712 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1418405 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1630155 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1966142 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3156. Min Act: -0.0000

Data Index: 258936 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3054. Min Act: 0.0000

Data Index: 972879 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1852414 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1847415 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1546506 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2704. Min Act: -0.0000

Data Index: 180988 (The Pile)

Max Activating Token Index: 629