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

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

Neuron 353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1907. Min Act: -0.0001

Data Index: 983533 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1095523 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1880. Min Act: -0.0001

Data Index: 454820 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1723. Min Act: -0.0001

Data Index: 998898 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1646. Min Act: -0.0001

Data Index: 98553 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1647. Min Act: -0.0001

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1481. Min Act: -0.0001

Data Index: 669526 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1521. Min Act: -0.0001

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1530. Min Act: -0.0001

Data Index: 827390 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1124311 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1659. Min Act: -0.0001

Data Index: 452825 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1500. Min Act: -0.0001

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1594. Min Act: -0.0001

Data Index: 373971 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1538. Min Act: -0.0001

Data Index: 518945 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1485. Min Act: -0.0001

Data Index: 919568 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1571. Min Act: -0.0001

Data Index: 818805 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1475. Min Act: -0.0001

Data Index: 546887 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1460. Min Act: -0.0001

Data Index: 247896 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1507. Min Act: -0.0001

Data Index: 924294 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1504. Min Act: -0.0001

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 906