Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5421 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4627. Min Act: -0.0000

Data Index: 270358 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4026. Min Act: -0.0000

Data Index: 923758 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4119. Min Act: -0.0000

Data Index: 291561 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3975. Min Act: -0.0000

Data Index: 551582 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3852. Min Act: -0.0000

Data Index: 808345 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3857. Min Act: -0.0000

Data Index: 662785 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3922. Min Act: -0.0000

Data Index: 591758 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3713. Min Act: -0.0000

Data Index: 638125 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3664. Min Act: -0.0000

Data Index: 466078 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3870. Min Act: 0.0000

Data Index: 663600 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.4023. Min Act: -0.0000

Data Index: 431463 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3487. Min Act: 0.0001

Data Index: 1244612 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3281. Min Act: -0.0000

Data Index: 924169 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3083. Min Act: -0.0000

Data Index: 602583 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1051993 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1210623 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3203. Min Act: -0.0000

Data Index: 347184 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1158585 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1209565 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.4627. Min Range: -0.4627

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 52