Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 339 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0001

Data Index: 191088 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1637214 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1202524 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1140517 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1357248 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1638256 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1826949 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0860. Min Act: -0.0001

Data Index: 757805 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1603708 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0834. Min Act: -0.0001

Data Index: 514676 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0743. Min Act: -0.0001

Data Index: 893481 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1509385 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0825. Min Act: -0.0001

Data Index: 199445 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1238809 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1918764 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1707168 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1141092 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1268162 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0770. Min Act: -0.0001

Data Index: 204853 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0760. Min Act: -0.0001

Data Index: 460321 (The Pile)

Max Activating Token Index: 730