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

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

Neuron 698 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1024614 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0806. Min Act: -0.0003

Data Index: 304609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0791. Min Act: -0.0003

Data Index: 28359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0722. Min Act: -0.0003

Data Index: 930110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1168289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1075831 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0576. Min Act: -0.0003

Data Index: 451224 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1369320 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0567. Min Act: -0.0003

Data Index: 211578 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1284681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0544. Min Act: -0.0003

Data Index: 556129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1169152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0551. Min Act: -0.0003

Data Index: 649981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1455998 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0519. Min Act: -0.0003

Data Index: 81354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1432003 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0522. Min Act: -0.0003

Data Index: 28744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0516. Min Act: -0.0003

Data Index: 196325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0497. Min Act: -0.0003

Data Index: 23046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1640564 (Python Code)

Max Activating Token Index: 1023