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

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

Neuron 2745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0484. Min Act: -0.0002

Data Index: 260687 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0508. Min Act: -0.0002

Data Index: 432016 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1079546 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0447. Min Act: -0.0002

Data Index: 385315 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1022366 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0428. Min Act: -0.0002

Data Index: 41572 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0445. Min Act: -0.0002

Data Index: 541779 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0454. Min Act: -0.0002

Data Index: 475159 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1046750 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0408. Min Act: -0.0002

Data Index: 754912 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1150908 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0451. Min Act: -0.0002

Data Index: 149736 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0448. Min Act: -0.0002

Data Index: 816010 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0429. Min Act: -0.0002

Data Index: 736906 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1099687 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0445. Min Act: -0.0002

Data Index: 267634 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1314 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0438. Min Act: -0.0002

Data Index: 398226 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1218259 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0422. Min Act: -0.0002

Data Index: 776984 (C4 (Web Text))

Max Activating Token Index: 916