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

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

Neuron 2785 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: 0.9014. Min Range: -0.9014

Max Act: 0.8591. Min Act: -0.0001

Data Index: 99644 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.9014. Min Act: -0.0001

Data Index: 931591 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8665. Min Act: -0.0001

Data Index: 660070 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1062499 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1122836 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8247. Min Act: -0.0001

Data Index: 700033 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7942. Min Act: -0.0000

Data Index: 823471 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1164350 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8038. Min Act: -0.0001

Data Index: 660524 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7465. Min Act: -0.0001

Data Index: 893246 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7345. Min Act: -0.0001

Data Index: 542867 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7606. Min Act: -0.0001

Data Index: 1309132 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7359. Min Act: -0.0001

Data Index: 619589 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1141595 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7371. Min Act: -0.0001

Data Index: 1070858 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7597. Min Act: -0.0001

Data Index: 957987 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.6796. Min Act: -0.0001

Data Index: 639619 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7063. Min Act: -0.0001

Data Index: 413973 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7170. Min Act: -0.0000

Data Index: 539747 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1267165 (C4 (Web Text))

Max Activating Token Index: 797