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

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

Neuron 506 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: 3.8072. Min Range: -3.8072

Max Act: 3.8072. Min Act: -0.0000

Data Index: 305983 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6592. Min Act: -0.0000

Data Index: 1103942 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.3093. Min Act: -0.0000

Data Index: 687278 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.8124. Min Act: -0.0000

Data Index: 1336987 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.7707. Min Act: -0.0000

Data Index: 1160330 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.8971. Min Act: -0.0000

Data Index: 767941 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.8328. Min Act: -0.0000

Data Index: 885858 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.4948. Min Act: -0.0000

Data Index: 935777 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.7854. Min Act: -0.0000

Data Index: 191371 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.5023. Min Act: -0.0000

Data Index: 809053 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.6275. Min Act: -0.0000

Data Index: 743107 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.5708. Min Act: -0.0000

Data Index: 432636 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.6783. Min Act: -0.0000

Data Index: 1332435 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.5600. Min Act: -0.0000

Data Index: 1074608 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.5461. Min Act: -0.0000

Data Index: 348737 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.6511. Min Act: -0.0000

Data Index: 1039783 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.6003. Min Act: -0.0000

Data Index: 1205375 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1016632 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.3911. Min Act: -0.0000

Data Index: 756069 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.8072. Min Range: -3.8072

Max Act: 2.4089. Min Act: -0.0000

Data Index: 530349 (C4 (Web Text))

Max Activating Token Index: 861