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

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

Neuron 90 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0577. Min Range: -1.0577

Max Act: 1.0577. Min Act: -0.0000

Data Index: 462166 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9675. Min Act: -0.0000

Data Index: 99789 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8706. Min Act: -0.0000

Data Index: 903797 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8741. Min Act: -0.0000

Data Index: 835348 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1047711 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8319. Min Act: -0.0000

Data Index: 330883 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8633. Min Act: -0.0000

Data Index: 365304 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8118. Min Act: 0.0000

Data Index: 735169 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7969. Min Act: -0.0000

Data Index: 566630 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7868. Min Act: -0.0000

Data Index: 712741 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7832. Min Act: -0.0000

Data Index: 140456 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7808. Min Act: -0.0000

Data Index: 259439 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7753. Min Act: -0.0000

Data Index: 466408 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7583. Min Act: -0.0000

Data Index: 446257 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7509. Min Act: -0.0000

Data Index: 903360 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7536. Min Act: -0.0000

Data Index: 870153 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7708. Min Act: -0.0000

Data Index: 790916 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7008. Min Act: -0.0000

Data Index: 795537 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7672. Min Act: 0.0000

Data Index: 1173052 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7598. Min Act: 0.0000

Data Index: 1349078 (C4 (Web Text))

Max Activating Token Index: 222