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

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

Neuron 3450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9575. Min Act: -0.0000

Data Index: 784094 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1248471 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9576. Min Act: -0.0000

Data Index: 76831 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9378. Min Act: -0.0000

Data Index: 705829 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9198. Min Act: -0.0000

Data Index: 605606 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1043586 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1250541 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.9510. Min Act: -0.0000

Data Index: 581767 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1048050 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.8249. Min Act: -0.0000

Data Index: 934495 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1187014 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1136775 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.8140. Min Act: -0.0000

Data Index: 329564 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7785. Min Act: -0.0000

Data Index: 956088 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7162. Min Act: -0.0000

Data Index: 919109 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1059913 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7762. Min Act: -0.0000

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1043357 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7590. Min Act: -0.0000

Data Index: 276875 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7507. Min Act: -0.0000

Data Index: 417226 (C4 (Web Text))

Max Activating Token Index: 891