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

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

Neuron 3243 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7597. Min Act: -0.0000

Data Index: 168733 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1068945 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7736. Min Act: -0.0000

Data Index: 212834 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8437. Min Act: -0.0000

Data Index: 359180 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.8020. Min Act: -0.0000

Data Index: 444675 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7828. Min Act: -0.0000

Data Index: 333767 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.7022. Min Act: -0.0000

Data Index: 323175 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6710. Min Act: -0.0000

Data Index: 321692 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1313106 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.6960. Min Act: -0.0000

Data Index: 844516 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4927. Min Act: -0.0000

Data Index: 602507 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1041867 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.5153. Min Act: -0.0000

Data Index: 346154 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4946. Min Act: 0.0000

Data Index: 436542 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4469. Min Act: -0.0000

Data Index: 838117 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4583. Min Act: -0.0000

Data Index: 965922 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4559. Min Act: -0.0000

Data Index: 350599 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4070. Min Act: -0.0000

Data Index: 374013 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4270. Min Act: -0.0000

Data Index: 288743 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.8437. Min Range: -0.8437

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1119969 (C4 (Web Text))

Max Activating Token Index: 644