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

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

Neuron 1169 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: 2.8641. Min Range: -2.8641

Max Act: 2.8121. Min Act: -0.0000

Data Index: 267982 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8641. Min Act: -0.0000

Data Index: 372638 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.4275. Min Act: -0.0000

Data Index: 1498970 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2718. Min Act: -0.0000

Data Index: 834993 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.3698. Min Act: -0.0000

Data Index: 547421 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.1703. Min Act: -0.0000

Data Index: 636375 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.1724. Min Act: -0.0000

Data Index: 803950 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2593. Min Act: -0.0000

Data Index: 96128 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.1098. Min Act: -0.0000

Data Index: 511354 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.3180. Min Act: -0.0000

Data Index: 1173574 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.1945. Min Act: -0.0000

Data Index: 1115835 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.1669. Min Act: -0.0000

Data Index: 206757 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0416. Min Act: -0.0000

Data Index: 889184 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2713. Min Act: -0.0000

Data Index: 180894 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2649. Min Act: -0.0000

Data Index: 9392 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2284. Min Act: -0.0000

Data Index: 623929 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2261. Min Act: -0.0000

Data Index: 249305 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.9917. Min Act: -0.0000

Data Index: 531370 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0876. Min Act: -0.0000

Data Index: 501142 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.9716. Min Act: -0.0000

Data Index: 807154 (C4 (Web Text))

Max Activating Token Index: 297