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

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

Neuron 4704 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1035079 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8878. Min Act: -0.0000

Data Index: 987599 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1011521 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8382. Min Act: -0.0000

Data Index: 426422 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7797. Min Act: -0.0000

Data Index: 404746 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8714. Min Act: -0.0000

Data Index: 594913 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8109. Min Act: -0.0000

Data Index: 932515 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7644. Min Act: -0.0000

Data Index: 555825 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.8073. Min Act: -0.0000

Data Index: 15459 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7922. Min Act: -0.0000

Data Index: 576743 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7788. Min Act: -0.0000

Data Index: 321158 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7344. Min Act: -0.0000

Data Index: 75253 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6621. Min Act: -0.0000

Data Index: 990090 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6920. Min Act: -0.0000

Data Index: 494067 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1168404 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1087707 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6335. Min Act: -0.0000

Data Index: 37311 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1159595 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6694. Min Act: -0.0000

Data Index: 634513 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.9251. Min Range: -0.9251

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1347956 (C4 (Web Text))

Max Activating Token Index: 597