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

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

Neuron 1674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2206. Min Act: -0.0001

Data Index: 469482 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2166. Min Act: -0.0001

Data Index: 539558 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2075. Min Act: -0.0001

Data Index: 847959 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.2002. Min Act: -0.0001

Data Index: 231474 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1906. Min Act: -0.0001

Data Index: 475198 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1837. Min Act: -0.0001

Data Index: 744956 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1239194 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1808. Min Act: -0.0001

Data Index: 652758 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1838. Min Act: -0.0001

Data Index: 604360 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1827. Min Act: -0.0001

Data Index: 309219 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1059075 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1719. Min Act: -0.0001

Data Index: 224531 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1156652 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1161284 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1751. Min Act: -0.0001

Data Index: 222631 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1726. Min Act: -0.0001

Data Index: 629641 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1725. Min Act: -0.0001

Data Index: 370906 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1130484 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1593. Min Act: -0.0001

Data Index: 930136 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.2206. Min Range: -0.2206

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1004847 (C4 (Web Text))

Max Activating Token Index: 59