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

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

Neuron 4515 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: 0.4895. Min Range: -0.4895

Max Act: 0.4895. Min Act: -0.0000

Data Index: 54157 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4456. Min Act: -0.0000

Data Index: 747555 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4627. Min Act: -0.0000

Data Index: 291647 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4138. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4094. Min Act: -0.0000

Data Index: 576038 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4059. Min Act: -0.0000

Data Index: 639307 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4102. Min Act: -0.0000

Data Index: 558777 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3834. Min Act: -0.0000

Data Index: 99109 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3671. Min Act: -0.0000

Data Index: 14293 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3696. Min Act: -0.0000

Data Index: 514840 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3399. Min Act: -0.0000

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3297. Min Act: -0.0000

Data Index: 785985 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3230. Min Act: -0.0000

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3127. Min Act: -0.0000

Data Index: 901071 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1220645 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.2888. Min Act: -0.0000

Data Index: 510180 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3101. Min Act: -0.0000

Data Index: 750211 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1275729 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3110. Min Act: -0.0000

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1126361 (C4 (Web Text))

Max Activating Token Index: 981