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

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

Neuron 4691 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1585202 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1438558 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1443633 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1611744 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1549855 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1565298 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1559297 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1481326 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1521445 (Python Code)

Max Activating Token Index: 672

Text #9

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1656529 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1653671 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1516772 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1517275 (Python Code)

Max Activating Token Index: 1003

Text #13

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1505968 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5531. Min Act: -0.0000

Data Index: 531057 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1641603 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1630889 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1249254 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1595812 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 0.9488. Min Range: -0.9488

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1466447 (Python Code)

Max Activating Token Index: 92