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

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

Neuron 3780 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: 1.2849. Min Range: -1.2849

Max Act: 1.2849. Min Act: -0.0000

Data Index: 362699 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0513. Min Act: -0.0000

Data Index: 894604 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9238. Min Act: -0.0000

Data Index: 370853 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9087. Min Act: -0.0000

Data Index: 921459 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9099. Min Act: -0.0000

Data Index: 756868 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8379. Min Act: -0.0000

Data Index: 998 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9427. Min Act: -0.0000

Data Index: 749410 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8750. Min Act: -0.0000

Data Index: 552690 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8493. Min Act: -0.0000

Data Index: 275553 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1291213 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1249011 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.7985. Min Act: -0.0000

Data Index: 613336 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8017. Min Act: -0.0000

Data Index: 259197 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.7944. Min Act: -0.0000

Data Index: 719699 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1089728 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.7707. Min Act: -0.0000

Data Index: 656276 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.7701. Min Act: -0.0000

Data Index: 916394 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1090432 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1224095 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8072. Min Act: -0.0000

Data Index: 558294 (C4 (Web Text))

Max Activating Token Index: 365