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

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

Neuron 3540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0002

Data Index: 106041 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1710. Min Act: -0.0002

Data Index: 509323 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1721. Min Act: -0.0002

Data Index: 613880 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1443. Min Act: -0.0002

Data Index: 147197 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1639. Min Act: -0.0002

Data Index: 1137400 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1589. Min Act: -0.0002

Data Index: 402631 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1596. Min Act: -0.0002

Data Index: 726379 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1497. Min Act: -0.0002

Data Index: 343999 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1592. Min Act: -0.0002

Data Index: 806119 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1108387 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1371. Min Act: -0.0002

Data Index: 427890 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1568. Min Act: -0.0002

Data Index: 883216 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1451. Min Act: -0.0002

Data Index: 692107 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1440. Min Act: -0.0002

Data Index: 25680 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1312731 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1476. Min Act: -0.0002

Data Index: 1190270 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1351824 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1586. Min Act: -0.0002

Data Index: 9810 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1517. Min Act: -0.0002

Data Index: 465547 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1415. Min Act: -0.0002

Data Index: 159573 (C4 (Web Text))

Max Activating Token Index: 572