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

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

Neuron 1003 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1021125 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0003

Data Index: 367976 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0704. Min Act: -0.0003

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1075078 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0678. Min Act: -0.0003

Data Index: 303201 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1295454 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0728. Min Act: -0.0003

Data Index: 48663 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1242072 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0733. Min Act: -0.0003

Data Index: 901983 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0677. Min Act: -0.0003

Data Index: 92713 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0699. Min Act: -0.0003

Data Index: 904396 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0696. Min Act: -0.0003

Data Index: 528332 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0710. Min Act: -0.0003

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1008580 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0667. Min Act: -0.0003

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0652. Min Act: -0.0003

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0703. Min Act: -0.0003

Data Index: 928404 (C4 (Web Text))

Max Activating Token Index: 271