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

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

Neuron 1231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.2876. Min Act: -0.0004

Data Index: 1550322 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.2789. Min Act: -0.0004

Data Index: 1532993 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.0520. Min Act: -0.0004

Data Index: 990734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.1309. Min Act: -0.0004

Data Index: 1595696 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.0836. Min Act: -0.0004

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.2876. Min Range: -1.2876

Max Act: 1.0121. Min Act: -0.0004

Data Index: 1371636 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9729. Min Act: -0.0004

Data Index: 551631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9832. Min Act: -0.0004

Data Index: 958559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9801. Min Act: -0.0004

Data Index: 1066650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9118. Min Act: -0.0004

Data Index: 1576876 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9203. Min Act: -0.0004

Data Index: 1574793 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.9408. Min Act: -0.0004

Data Index: 1563583 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8671. Min Act: -0.0004

Data Index: 1314039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8459. Min Act: -0.0004

Data Index: 1136437 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8814. Min Act: -0.0004

Data Index: 1519857 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8616. Min Act: -0.0004

Data Index: 160736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8802. Min Act: -0.0004

Data Index: 1454146 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8771. Min Act: -0.0003

Data Index: 1423838 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8504. Min Act: -0.0004

Data Index: 1487546 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.2876. Min Range: -1.2876

Max Act: 0.8488. Min Act: -0.0004

Data Index: 645076 (C4 (Web Text))

Max Activating Token Index: 1023