Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.7776. Min Act: -0.0001

Data Index: 539797 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6924. Min Act: -0.0000

Data Index: 834660 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.7050. Min Act: -0.0001

Data Index: 1209405 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6544. Min Act: -0.0001

Data Index: 1232082 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6606. Min Act: -0.0001

Data Index: 856869 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1106280 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6100. Min Act: -0.0000

Data Index: 240653 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5944. Min Act: -0.0000

Data Index: 197844 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5755. Min Act: -0.0001

Data Index: 49943 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1040395 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5577. Min Act: -0.0000

Data Index: 40573 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1356668 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5941. Min Act: -0.0001

Data Index: 39813 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5724. Min Act: -0.0001

Data Index: 1155791 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5262. Min Act: -0.0001

Data Index: 483454 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1126080 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5446. Min Act: -0.0001

Data Index: 935144 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5259. Min Act: -0.0001

Data Index: 478690 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5216. Min Act: -0.0001

Data Index: 1265355 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5022. Min Act: -0.0000

Data Index: 359800 (C4 (Web Text))

Max Activating Token Index: 1022