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

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

Neuron 2591 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1322733 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5329. Min Act: -0.0000

Data Index: 723030 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5141. Min Act: -0.0000

Data Index: 113869 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5287. Min Act: -0.0000

Data Index: 346528 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5013. Min Act: -0.0000

Data Index: 445006 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1163845 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3954. Min Act: -0.0000

Data Index: 768197 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3909. Min Act: -0.0000

Data Index: 376589 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3886. Min Act: -0.0000

Data Index: 828537 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1099053 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3889. Min Act: -0.0000

Data Index: 705441 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4025. Min Act: -0.0000

Data Index: 606323 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3835. Min Act: -0.0000

Data Index: 164326 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3876. Min Act: -0.0000

Data Index: 259415 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3993. Min Act: -0.0000

Data Index: 20156 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3796. Min Act: -0.0000

Data Index: 201582 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3814. Min Act: -0.0000

Data Index: 174069 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3748. Min Act: -0.0000

Data Index: 962379 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3631. Min Act: -0.0000

Data Index: 926176 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.3666. Min Act: -0.0000

Data Index: 427271 (C4 (Web Text))

Max Activating Token Index: 684