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

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

Neuron 387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1730. Min Act: -0.0003

Data Index: 182073 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1525. Min Act: -0.0003

Data Index: 1257657 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1732. Min Act: -0.0003

Data Index: 869489 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1562. Min Act: -0.0003

Data Index: 660594 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1578. Min Act: -0.0003

Data Index: 138531 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1734. Min Act: -0.0003

Data Index: 990662 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1488. Min Act: -0.0003

Data Index: 1278867 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1694. Min Act: -0.0003

Data Index: 264435 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1504. Min Act: -0.0003

Data Index: 261746 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1563. Min Act: -0.0003

Data Index: 159110 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1544. Min Act: -0.0003

Data Index: 808257 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1425. Min Act: -0.0003

Data Index: 234260 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1439. Min Act: -0.0003

Data Index: 892738 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1370. Min Act: -0.0003

Data Index: 901130 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1423. Min Act: -0.0003

Data Index: 1246778 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1346. Min Act: -0.0003

Data Index: 434215 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1341. Min Act: -0.0003

Data Index: 1266952 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1427. Min Act: -0.0003

Data Index: 49161 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1426. Min Act: -0.0003

Data Index: 1253433 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1426. Min Act: -0.0003

Data Index: 1051472 (C4 (Web Text))

Max Activating Token Index: 4