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

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

Neuron 3340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0001

Data Index: 450609 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0870. Min Act: -0.0001

Data Index: 34657 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0804. Min Act: -0.0001

Data Index: 466847 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0809. Min Act: -0.0001

Data Index: 261895 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1320436 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0773. Min Act: -0.0001

Data Index: 430695 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0769. Min Act: -0.0001

Data Index: 734314 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1128978 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0762. Min Act: -0.0001

Data Index: 2663 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0761. Min Act: -0.0001

Data Index: 629518 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0763. Min Act: -0.0001

Data Index: 509877 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0755. Min Act: -0.0001

Data Index: 905284 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0765. Min Act: -0.0001

Data Index: 787051 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0762. Min Act: -0.0001

Data Index: 517292 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1166762 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0754. Min Act: -0.0001

Data Index: 823700 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0746. Min Act: -0.0001

Data Index: 21933 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0748. Min Act: -0.0001

Data Index: 180660 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0739. Min Act: -0.0001

Data Index: 400215 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0725. Min Act: -0.0001

Data Index: 589408 (C4 (Web Text))

Max Activating Token Index: 321