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

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

Neuron 3287 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0748. Min Act: -0.0002

Data Index: 609323 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0002

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0787. Min Act: -0.0002

Data Index: 524305 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0751. Min Act: -0.0002

Data Index: 237713 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0740. Min Act: -0.0002

Data Index: 26443 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1128416 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0722. Min Act: -0.0002

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0707. Min Act: -0.0002

Data Index: 545141 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0677. Min Act: -0.0002

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0632. Min Act: -0.0002

Data Index: 527791 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0641. Min Act: -0.0002

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0667. Min Act: -0.0002

Data Index: 226683 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0615. Min Act: -0.0002

Data Index: 990179 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0632. Min Act: -0.0002

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0610. Min Act: -0.0002

Data Index: 974111 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0577. Min Act: -0.0002

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0647. Min Act: -0.0002

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 755