Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 505 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.2092. Min Act: -0.0001

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1963. Min Act: -0.0001

Data Index: 470260 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1980. Min Act: -0.0001

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1779. Min Act: -0.0001

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1858. Min Act: -0.0001

Data Index: 150643 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1889. Min Act: -0.0001

Data Index: 635581 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1917. Min Act: -0.0001

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1714. Min Act: -0.0001

Data Index: 720139 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1658. Min Act: -0.0001

Data Index: 653318 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1698. Min Act: -0.0001

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1680. Min Act: -0.0001

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1665. Min Act: -0.0001

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1277426 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1521. Min Act: -0.0001

Data Index: 420640 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1477. Min Act: -0.0001

Data Index: 172803 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1466. Min Act: -0.0002

Data Index: 381568 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1510. Min Act: -0.0002

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1432. Min Act: -0.0001

Data Index: 885314 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1088334 (C4 (Web Text))

Max Activating Token Index: 944