Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1251 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2191. Min Act: -0.0003

Data Index: 98627 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1814. Min Act: -0.0003

Data Index: 664295 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1606. Min Act: -0.0003

Data Index: 34721 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1789. Min Act: -0.0003

Data Index: 1164352 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1709. Min Act: -0.0003

Data Index: 1163495 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1646. Min Act: -0.0003

Data Index: 121275 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1628. Min Act: -0.0003

Data Index: 1127718 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1624. Min Act: -0.0003

Data Index: 364039 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1636. Min Act: -0.0003

Data Index: 1201020 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1544. Min Act: -0.0003

Data Index: 305919 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1590. Min Act: -0.0003

Data Index: 147939 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1480. Min Act: -0.0003

Data Index: 758438 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1527. Min Act: -0.0003

Data Index: 100720 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1329338 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1508. Min Act: -0.0003

Data Index: 168487 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1515. Min Act: -0.0003

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1598. Min Act: -0.0003

Data Index: 812560 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1525. Min Act: -0.0003

Data Index: 1109830 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1415. Min Act: -0.0003

Data Index: 700457 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1480. Min Act: -0.0003

Data Index: 228703 (C4 (Web Text))

Max Activating Token Index: 875