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

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

Neuron 33 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: 0.7487. Min Range: -0.7487

Max Act: 0.7487. Min Act: -0.0001

Data Index: 257620 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.7074. Min Act: -0.0000

Data Index: 123731 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.7104. Min Act: -0.0000

Data Index: 473041 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5978. Min Act: -0.0000

Data Index: 869617 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5622. Min Act: -0.0000

Data Index: 364378 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1298768 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5691. Min Act: -0.0000

Data Index: 748442 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1173561 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5547. Min Act: -0.0000

Data Index: 611072 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1747 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5615. Min Act: -0.0000

Data Index: 917752 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1069624 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5563. Min Act: -0.0000

Data Index: 692564 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5305. Min Act: -0.0001

Data Index: 1569163 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1606156 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5253. Min Act: -0.0000

Data Index: 360594 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5357. Min Act: -0.0000

Data Index: 548772 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5141. Min Act: -0.0000

Data Index: 257473 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.4859. Min Act: -0.0000

Data Index: 562523 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1543779 (Python Code)

Max Activating Token Index: 1019