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

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

Neuron 3975 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.9881. Min Act: -0.0001

Data Index: 417384 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.5403. Min Act: -0.0001

Data Index: 1112079 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.4741. Min Act: -0.0001

Data Index: 590244 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.1896. Min Act: -0.0001

Data Index: 1290744 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.1970. Min Act: -0.0001

Data Index: 1141650 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.1280. Min Act: -0.0001

Data Index: 1364962 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 1.9881. Min Range: -1.9881

Max Act: 1.0127. Min Act: -0.0001

Data Index: 1037784 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.9214. Min Act: -0.0001

Data Index: 1555685 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8291. Min Act: -0.0001

Data Index: 604337 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.9068. Min Act: -0.0001

Data Index: 830141 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8560. Min Act: -0.0001

Data Index: 386822 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8355. Min Act: -0.0001

Data Index: 1152882 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.7978. Min Act: -0.0001

Data Index: 309482 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8742. Min Act: -0.0001

Data Index: 223582 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.9338. Min Act: -0.0001

Data Index: 966834 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8408. Min Act: -0.0001

Data Index: 1325923 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8757. Min Act: -0.0001

Data Index: 658582 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8178. Min Act: -0.0001

Data Index: 136874 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8603. Min Act: -0.0001

Data Index: 176678 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.9881. Min Range: -1.9881

Max Act: 0.8639. Min Act: -0.0001

Data Index: 220520 (C4 (Web Text))

Max Activating Token Index: 771