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

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

Neuron 3067 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1414664 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0708. Min Act: -0.0001

Data Index: 753671 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0590. Min Act: -0.0001

Data Index: 167715 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0558. Min Act: -0.0001

Data Index: 361062 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0568. Min Act: -0.0001

Data Index: 831457 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0497. Min Act: -0.0001

Data Index: 987011 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0566. Min Act: -0.0001

Data Index: 312699 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1336997 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0528. Min Act: -0.0001

Data Index: 839127 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1328828 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0516. Min Act: -0.0001

Data Index: 502452 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0536. Min Act: -0.0001

Data Index: 45800 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0566. Min Act: -0.0001

Data Index: 249032 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0535. Min Act: -0.0001

Data Index: 412824 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1112606 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1221974 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1260536 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0526. Min Act: -0.0001

Data Index: 331084 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0519. Min Act: -0.0001

Data Index: 836695 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1213539 (C4 (Web Text))

Max Activating Token Index: 969