Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1500 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1172649 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1085491 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1704. Min Act: -0.0001

Data Index: 438771 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1729. Min Act: -0.0001

Data Index: 26595 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1666. Min Act: -0.0001

Data Index: 437137 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1719. Min Act: -0.0001

Data Index: 114662 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1644. Min Act: -0.0001

Data Index: 578846 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1174566 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1638. Min Act: -0.0001

Data Index: 432374 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1618. Min Act: -0.0001

Data Index: 323393 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1743. Min Act: -0.0001

Data Index: 846599 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1670. Min Act: -0.0001

Data Index: 619236 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1662. Min Act: -0.0001

Data Index: 532555 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1645. Min Act: -0.0001

Data Index: 980532 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1600. Min Act: -0.0001

Data Index: 723050 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1701. Min Act: -0.0001

Data Index: 475948 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1643. Min Act: -0.0001

Data Index: 368316 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1546. Min Act: -0.0001

Data Index: 304395 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1645. Min Act: -0.0001

Data Index: 497656 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1682. Min Act: -0.0001

Data Index: 177404 (C4 (Web Text))

Max Activating Token Index: 341