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

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

Neuron 4001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3591. Min Act: -0.0000

Data Index: 993906 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3894. Min Act: -0.0000

Data Index: 833271 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3875. Min Act: -0.0000

Data Index: 120551 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3354. Min Act: -0.0000

Data Index: 561265 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3197. Min Act: -0.0000

Data Index: 425000 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1185510 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3062. Min Act: -0.0000

Data Index: 694515 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3293. Min Act: -0.0000

Data Index: 293169 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3215. Min Act: -0.0000

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3203. Min Act: -0.0000

Data Index: 626483 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3056. Min Act: -0.0000

Data Index: 530824 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3601. Min Act: -0.0000

Data Index: 620159 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.2921. Min Act: -0.0000

Data Index: 573541 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3017. Min Act: -0.0000

Data Index: 832017 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3354. Min Act: -0.0000

Data Index: 838392 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3024. Min Act: -0.0000

Data Index: 238747 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.2589. Min Act: -0.0000

Data Index: 561159 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1217423 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.3062. Min Act: -0.0000

Data Index: 882570 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.3894. Min Range: -0.3894

Max Act: 0.2660. Min Act: -0.0000

Data Index: 114573 (C4 (Web Text))

Max Activating Token Index: 428