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

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

Neuron 335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.8908. Min Act: -0.0000

Data Index: 267019 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.8208. Min Act: -0.0000

Data Index: 434523 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.7717. Min Act: -0.0000

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.6967. Min Act: -0.0000

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.7680. Min Act: -0.0000

Data Index: 187500 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.5676. Min Act: -0.0000

Data Index: 123606 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.5546. Min Act: -0.0000

Data Index: 112035 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.4854. Min Act: -0.0000

Data Index: 547359 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.3954. Min Act: -0.0000

Data Index: 614471 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1227126 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.4561. Min Act: -0.0000

Data Index: 1240499 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.3017. Min Act: -0.0000

Data Index: 638364 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.4196. Min Act: -0.0000

Data Index: 862731 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.4057. Min Act: -0.0000

Data Index: 707246 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.3580. Min Act: -0.0000

Data Index: 744535 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.2530. Min Act: -0.0000

Data Index: 177566 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.3834. Min Act: -0.0000

Data Index: 624934 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.3470. Min Act: -0.0000

Data Index: 1327531 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.1014. Min Act: -0.0000

Data Index: 550815 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.8908. Min Range: -2.8908

Max Act: 2.2796. Min Act: -0.0000

Data Index: 309121 (C4 (Web Text))

Max Activating Token Index: 250