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

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

Neuron 3616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1719. Min Range: -2.1719

Max Act: 2.1719. Min Act: -0.0000

Data Index: 805286 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1138014 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.2168. Min Act: -0.0000

Data Index: 147185 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.2448. Min Act: -0.0000

Data Index: 165322 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0555. Min Act: -0.0000

Data Index: 230403 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1201566 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.1132. Min Act: -0.0000

Data Index: 620405 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1240753 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1047496 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.9789. Min Act: -0.0000

Data Index: 261245 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0117. Min Act: -0.0000

Data Index: 663537 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1141635 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1325256 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 2.1719. Min Range: -2.1719

Max Act: 1.0533. Min Act: -0.0000

Data Index: 85582 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.9343. Min Act: -0.0000

Data Index: 362980 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1180001 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.9721. Min Act: -0.0000

Data Index: 872816 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.8920. Min Act: -0.0000

Data Index: 952749 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1311663 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.1719. Min Range: -2.1719

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1017724 (C4 (Web Text))

Max Activating Token Index: 119