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

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

Neuron 3624 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: 1.5065. Min Range: -1.5065

Max Act: 1.5065. Min Act: -0.0001

Data Index: 705562 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.4132. Min Act: -0.0001

Data Index: 255507 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.3891. Min Act: -0.0001

Data Index: 603160 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.2993. Min Act: -0.0001

Data Index: 1089649 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.2837. Min Act: -0.0001

Data Index: 969687 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1975. Min Act: -0.0001

Data Index: 848320 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1605. Min Act: -0.0001

Data Index: 467514 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1495. Min Act: -0.0001

Data Index: 272512 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.2162. Min Act: -0.0001

Data Index: 1253152 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1025. Min Act: -0.0001

Data Index: 1339426 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1480. Min Act: -0.0001

Data Index: 655488 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1038. Min Act: -0.0001

Data Index: 711468 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1660. Min Act: -0.0001

Data Index: 744352 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.0601. Min Act: -0.0001

Data Index: 1030978 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1497. Min Act: -0.0001

Data Index: 303330 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1407. Min Act: -0.0001

Data Index: 90137 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1459. Min Act: -0.0001

Data Index: 1331746 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1605. Min Act: -0.0001

Data Index: 986113 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.1667. Min Act: -0.0001

Data Index: 567483 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.5065. Min Range: -1.5065

Max Act: 1.0905. Min Act: -0.0001

Data Index: 43664 (C4 (Web Text))

Max Activating Token Index: 224