Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1037228 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1651. Min Act: -0.0000

Data Index: 755444 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1642. Min Act: -0.0000

Data Index: 943319 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1883. Min Act: -0.0001

Data Index: 807716 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1723. Min Act: -0.0001

Data Index: 663325 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0000

Data Index: 605800 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1721. Min Act: -0.0001

Data Index: 692885 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1335614 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1231941 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1559. Min Act: -0.0001

Data Index: 711637 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1787. Min Act: -0.0000

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1495. Min Act: -0.0000

Data Index: 753537 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1450. Min Act: -0.0001

Data Index: 523749 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1639. Min Act: -0.0000

Data Index: 815095 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1662. Min Act: -0.0001

Data Index: 742510 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1601. Min Act: -0.0000

Data Index: 822807 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1007029 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1062843 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1020958 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1648. Min Act: -0.0000

Data Index: 55099 (C4 (Web Text))

Max Activating Token Index: 714