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

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

Neuron 3398 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: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0002

Data Index: 876257 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1009605 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0649. Min Act: -0.0002

Data Index: 278115 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1188686 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0621. Min Act: -0.0002

Data Index: 739197 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1237527 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1062054 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1211864 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0648. Min Act: -0.0002

Data Index: 116123 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0619. Min Act: -0.0002

Data Index: 86994 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1004886 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0561. Min Act: -0.0002

Data Index: 254959 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0591. Min Act: -0.0002

Data Index: 207402 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1219001 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0551. Min Act: -0.0002

Data Index: 945639 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1157876 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0551. Min Act: -0.0002

Data Index: 427641 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0550. Min Act: -0.0002

Data Index: 494938 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1067601 (C4 (Web Text))

Max Activating Token Index: 246