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

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

Neuron 584 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.5117. Min Act: -0.0000

Data Index: 1303779 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.2441. Min Act: -0.0000

Data Index: 1167264 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.2353. Min Act: -0.0000

Data Index: 801755 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.1663. Min Act: -0.0000

Data Index: 1344688 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.1237. Min Act: -0.0000

Data Index: 602302 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.1060. Min Act: -0.0000

Data Index: 354533 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.9804. Min Act: -0.0000

Data Index: 734532 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0550. Min Act: -0.0000

Data Index: 899756 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0112. Min Act: -0.0000

Data Index: 556731 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.9945. Min Act: -0.0000

Data Index: 882737 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0927. Min Act: -0.0000

Data Index: 725425 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1211609 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0505. Min Act: -0.0000

Data Index: 662499 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0345. Min Act: -0.0000

Data Index: 1144607 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0496. Min Act: -0.0000

Data Index: 936018 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 2.5117. Min Range: -2.5117

Max Act: 2.0042. Min Act: -0.0000

Data Index: 1042423 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.7724. Min Act: -0.0000

Data Index: 460607 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.8851. Min Act: -0.0000

Data Index: 684635 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1273427 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 2.5117. Min Range: -2.5117

Max Act: 1.8566. Min Act: -0.0000

Data Index: 275925 (C4 (Web Text))

Max Activating Token Index: 594