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

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

Neuron 2947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1932. Min Act: -0.0001

Data Index: 750840 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1826. Min Act: -0.0001

Data Index: 974277 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1086460 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1752. Min Act: -0.0001

Data Index: 630997 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1784. Min Act: -0.0001

Data Index: 554871 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1650. Min Act: -0.0001

Data Index: 178323 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1317055 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1685. Min Act: -0.0001

Data Index: 196523 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1053371 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1265815 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1256182 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1351885 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1689. Min Act: -0.0001

Data Index: 737267 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1074878 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1612. Min Act: -0.0001

Data Index: 860094 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1571. Min Act: -0.0001

Data Index: 709593 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1519. Min Act: -0.0001

Data Index: 129569 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1661. Min Act: -0.0001

Data Index: 247763 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1551. Min Act: -0.0001

Data Index: 6017 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1592. Min Act: -0.0001

Data Index: 314737 (C4 (Web Text))

Max Activating Token Index: 423