Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 78 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0005

Data Index: 853974 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0550. Min Act: -0.0005

Data Index: 1084739 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0548. Min Act: -0.0005

Data Index: 128906 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0556. Min Act: -0.0005

Data Index: 1318803 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0553. Min Act: -0.0005

Data Index: 30967 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0506. Min Act: -0.0005

Data Index: 311481 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0499. Min Act: -0.0005

Data Index: 466754 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0517. Min Act: -0.0005

Data Index: 377527 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0526. Min Act: -0.0005

Data Index: 458188 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0526. Min Act: -0.0005

Data Index: 580834 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0535. Min Act: -0.0005

Data Index: 790633 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0539. Min Act: -0.0005

Data Index: 1237967 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0521. Min Act: -0.0005

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0522. Min Act: -0.0005

Data Index: 174631 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0525. Min Act: -0.0005

Data Index: 866933 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0485. Min Act: -0.0005

Data Index: 452583 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0522. Min Act: -0.0005

Data Index: 1187362 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0517. Min Act: -0.0005

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0478. Min Act: -0.0005

Data Index: 1064417 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1045159 (C4 (Web Text))

Max Activating Token Index: 986