Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 37 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7783. Min Act: -0.0000

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7693. Min Act: -0.0000

Data Index: 61718 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7891. Min Act: -0.0000

Data Index: 206415 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6819. Min Act: -0.0000

Data Index: 632339 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1133395 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7539. Min Act: -0.0000

Data Index: 914167 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7256. Min Act: -0.0000

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7453. Min Act: -0.0000

Data Index: 288580 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1193881 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6936. Min Act: -0.0001

Data Index: 270460 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6788. Min Act: -0.0000

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6799. Min Act: -0.0000

Data Index: 176718 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6451. Min Act: -0.0000

Data Index: 24222 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6481. Min Act: -0.0001

Data Index: 576685 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6113. Min Act: -0.0001

Data Index: 255683 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6845. Min Act: -0.0001

Data Index: 242120 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6139. Min Act: -0.0000

Data Index: 678011 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5850. Min Act: -0.0000

Data Index: 208674 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1153000 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6172. Min Act: -0.0001

Data Index: 834785 (C4 (Web Text))

Max Activating Token Index: 320