Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0005

Data Index: 261655 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1273147 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0401. Min Act: -0.0005

Data Index: 235842 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0396. Min Act: -0.0005

Data Index: 1093090 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0386. Min Act: -0.0005

Data Index: 837132 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0393. Min Act: -0.0004

Data Index: 1206222 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0394. Min Act: -0.0005

Data Index: 1130783 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0381. Min Act: -0.0004

Data Index: 281171 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1313569 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0376. Min Act: -0.0004

Data Index: 1307909 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0384. Min Act: -0.0004

Data Index: 374085 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0383. Min Act: -0.0004

Data Index: 100047 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0383. Min Act: -0.0004

Data Index: 538817 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0375. Min Act: -0.0004

Data Index: 606333 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0381. Min Act: -0.0004

Data Index: 894130 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0381. Min Act: -0.0004

Data Index: 590460 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1160873 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0378. Min Act: -0.0005

Data Index: 628460 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0370. Min Act: -0.0004

Data Index: 515835 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0386. Min Act: -0.0005

Data Index: 778367 (C4 (Web Text))

Max Activating Token Index: 18