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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1210735 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5499. Min Act: -0.0000

Data Index: 43494 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4632. Min Act: -0.0000

Data Index: 532711 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4805. Min Act: -0.0000

Data Index: 436753 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1157233 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4030. Min Act: -0.0000

Data Index: 974107 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4123. Min Act: -0.0000

Data Index: 665366 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4033. Min Act: -0.0000

Data Index: 159552 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3829. Min Act: -0.0000

Data Index: 403294 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1274330 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4078. Min Act: -0.0000

Data Index: 897553 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3909. Min Act: -0.0000

Data Index: 647724 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3787. Min Act: -0.0000

Data Index: 445323 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3954. Min Act: -0.0000

Data Index: 313624 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3632. Min Act: -0.0000

Data Index: 787349 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3717. Min Act: -0.0000

Data Index: 500145 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3478. Min Act: -0.0000

Data Index: 529792 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3585. Min Act: -0.0000

Data Index: 85734 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1077641 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3668. Min Act: -0.0000

Data Index: 250802 (C4 (Web Text))

Max Activating Token Index: 758