Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1408910 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1519655 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1566851 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1599310 (Python Code)

Max Activating Token Index: 682

Text #4

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1637443 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2697. Min Act: -0.0001

Data Index: 1429069 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1557486 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1456706 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1412321 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1398062 (Python Code)

Max Activating Token Index: 902

Text #10

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1466094 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1593214 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1515235 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1401676 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2612. Min Act: -0.0001

Data Index: 1423510 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2541. Min Act: -0.0001

Data Index: 1565705 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1599456 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1617669 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1456877 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2451. Min Act: -0.0001

Data Index: 1387800 (Python Code)

Max Activating Token Index: 665