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

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

Neuron 239 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1573. Min Range: -7.1573

Max Act: 7.1573. Min Act: -0.0000

Data Index: 180440 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.7692. Min Act: -0.0000

Data Index: 596491 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 7.1573. Min Range: -7.1573

Max Act: 6.1534. Min Act: -0.0001

Data Index: 421398 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.5195. Min Act: -0.0000

Data Index: 1040168 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.4121. Min Act: -0.0000

Data Index: 281730 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.3902. Min Act: -0.0000

Data Index: 1242614 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.6175. Min Act: -0.0000

Data Index: 364881 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.2541. Min Act: -0.0000

Data Index: 823200 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.3444. Min Act: -0.0000

Data Index: 1348379 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.2738. Min Act: -0.0000

Data Index: 295679 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.6087. Min Act: -0.0000

Data Index: 847267 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.0185. Min Act: -0.0000

Data Index: 876638 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.3345. Min Act: -0.0000

Data Index: 205841 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.1503. Min Act: -0.0000

Data Index: 1005458 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.3095. Min Act: -0.0001

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.0888. Min Act: -0.0000

Data Index: 1329681 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 7.1573. Min Range: -7.1573

Max Act: 4.8798. Min Act: -0.0000

Data Index: 316664 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 7.1573. Min Range: -7.1573

Max Act: 4.8170. Min Act: -0.0000

Data Index: 453801 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 7.1573. Min Range: -7.1573

Max Act: 5.1819. Min Act: -0.0000

Data Index: 1165611 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 7.1573. Min Range: -7.1573

Max Act: 4.7497. Min Act: -0.0000

Data Index: 1150108 (C4 (Web Text))

Max Activating Token Index: 64