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

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

Neuron 3164 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1551134 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6835. Min Act: -0.0000

Data Index: 405735 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6851. Min Act: -0.0000

Data Index: 500191 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6546. Min Act: -0.0000

Data Index: 909157 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6552. Min Act: -0.0000

Data Index: 636998 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6399. Min Act: -0.0000

Data Index: 803486 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1161653 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1179311 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6229. Min Act: -0.0000

Data Index: 859672 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5915. Min Act: -0.0000

Data Index: 377305 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5815. Min Act: -0.0000

Data Index: 615022 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1275746 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5921. Min Act: -0.0000

Data Index: 960719 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1165931 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5952. Min Act: -0.0000

Data Index: 197249 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1633451 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1288720 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5521. Min Act: -0.0000

Data Index: 878130 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1471246 (Python Code)

Max Activating Token Index: 888

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1361454 (Python Code)

Max Activating Token Index: 434