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

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

Neuron 4106 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: 1.2648. Min Range: -1.2648

Max Act: 1.2648. Min Act: -0.0000

Data Index: 190844 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1034334 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8920. Min Act: -0.0000

Data Index: 533 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.9598. Min Act: -0.0000

Data Index: 563606 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8321. Min Act: -0.0000

Data Index: 506940 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1330900 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1253412 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8142. Min Act: -0.0000

Data Index: 634592 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7967. Min Act: -0.0000

Data Index: 424555 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7914. Min Act: -0.0000

Data Index: 627324 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8146. Min Act: -0.0000

Data Index: 857966 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1171297 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8139. Min Act: -0.0000

Data Index: 195567 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8011. Min Act: -0.0000

Data Index: 965459 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.8152. Min Act: -0.0000

Data Index: 880354 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7453. Min Act: -0.0000

Data Index: 43172 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7204. Min Act: -0.0000

Data Index: 338899 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7657. Min Act: -0.0000

Data Index: 693991 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7355. Min Act: -0.0000

Data Index: 346705 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.2648. Min Range: -1.2648

Max Act: 0.7508. Min Act: -0.0000

Data Index: 993892 (C4 (Web Text))

Max Activating Token Index: 542