Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1288 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.9893. Min Act: -0.0000

Data Index: 1622040 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.8675. Min Act: -0.0000

Data Index: 1501546 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.9809. Min Act: -0.0000

Data Index: 1582251 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.1033. Min Act: -0.0000

Data Index: 1382807 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.3125. Min Act: -0.0000

Data Index: 1442226 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.0597. Min Act: -0.0000

Data Index: 1482661 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.0256. Min Act: -0.0000

Data Index: 1587405 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.8351. Min Act: -0.0000

Data Index: 1642535 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.1110. Min Act: -0.0000

Data Index: 1633846 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.8054. Min Act: -0.0000

Data Index: 1629780 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.7999. Min Act: -0.0000

Data Index: 1616561 (Python Code)

Max Activating Token Index: 736

Text #11

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.2563. Min Act: -0.0000

Data Index: 1547169 (Python Code)

Max Activating Token Index: 121

Text #12

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.5703. Min Act: -0.0000

Data Index: 1397232 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.8583. Min Act: -0.0000

Data Index: 1447101 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.8438. Min Act: -0.0000

Data Index: 1523605 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.3522. Min Act: -0.0000

Data Index: 1394577 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.9914. Min Act: -0.0000

Data Index: 1530981 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.6251. Min Act: -0.0000

Data Index: 1588538 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 4.9893. Min Range: -4.9893

Max Act: 3.6453. Min Act: -0.0000

Data Index: 1546717 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 4.9893. Min Range: -4.9893

Max Act: 4.0061. Min Act: -0.0000

Data Index: 1422139 (Python Code)

Max Activating Token Index: 660