Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0339. Min Act: -0.0001

Data Index: 87268 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8719. Min Act: -0.0001

Data Index: 52872 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1331931 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8403. Min Act: -0.0001

Data Index: 571615 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7474. Min Act: -0.0001

Data Index: 897961 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0087. Min Act: -0.0001

Data Index: 1266118 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7813. Min Act: -0.0001

Data Index: 793657 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7756. Min Act: -0.0001

Data Index: 891079 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1037940 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1120341 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8449. Min Act: -0.0001

Data Index: 966576 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7852. Min Act: -0.0001

Data Index: 97445 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8200. Min Act: -0.0001

Data Index: 290574 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9036. Min Act: -0.0001

Data Index: 687606 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1233621 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7352. Min Act: -0.0001

Data Index: 170157 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8371. Min Act: -0.0001

Data Index: 918717 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1184668 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8407. Min Act: -0.0001

Data Index: 988093 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7889. Min Act: -0.0001

Data Index: 457931 (C4 (Web Text))

Max Activating Token Index: 8