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

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

Neuron 2012 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: 0.1752. Min Range: -0.1752

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1701. Min Act: -0.0000

Data Index: 61673 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1659. Min Act: -0.0000

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1518. Min Act: -0.0001

Data Index: 121499 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1559. Min Act: -0.0000

Data Index: 60117 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1333. Min Act: -0.0000

Data Index: 811313 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1634. Min Act: -0.0001

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1314. Min Act: -0.0001

Data Index: 163522 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1410. Min Act: -0.0001

Data Index: 839116 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1424. Min Act: -0.0001

Data Index: 499916 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1630. Min Act: -0.0000

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1077753 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1098241 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1384. Min Act: -0.0000

Data Index: 2860 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1102136 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1436. Min Act: -0.0001

Data Index: 54592 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1464. Min Act: -0.0001

Data Index: 123204 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1424. Min Act: -0.0000

Data Index: 78521 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1472. Min Act: -0.0000

Data Index: 45250 (C4 (Web Text))

Max Activating Token Index: 324