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

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

Neuron 2155 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: 0.9993. Min Range: -0.9993

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1424570 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1628088 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1650056 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1379898 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1580861 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1526587 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1478782 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8129. Min Act: -0.0000

Data Index: 162067 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1589337 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1433549 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1589017 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5709. Min Act: -0.0000

Data Index: 678952 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1455374 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1491489 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1511912 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1553491 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5045. Min Act: -0.0000

Data Index: 16655 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1496477 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1533584 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1551045 (Python Code)

Max Activating Token Index: 370