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

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

Neuron 3869 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: 3.5024. Min Range: -3.5024

Max Act: 3.0952. Min Act: -0.0001

Data Index: 1404740 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.5024. Min Act: -0.0000

Data Index: 1646567 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.0052. Min Act: -0.0000

Data Index: 1288913 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.7348. Min Act: -0.0000

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.2879. Min Act: -0.0000

Data Index: 179757 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.3964. Min Act: -0.0001

Data Index: 1393886 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1376739 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.3876. Min Act: -0.0000

Data Index: 1447495 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.5147. Min Act: -0.0000

Data Index: 1049125 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.3541. Min Act: -0.0000

Data Index: 1488788 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.1374. Min Act: -0.0000

Data Index: 1375366 (Python Code)

Max Activating Token Index: 278

Text #11

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.3693. Min Act: -0.0000

Data Index: 369631 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1453573 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 3.5024. Min Range: -3.5024

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1484101 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.0584. Min Act: -0.0001

Data Index: 1405594 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.2676. Min Act: -0.0000

Data Index: 719323 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.0433. Min Act: -0.0000

Data Index: 1376530 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.2628. Min Act: -0.0000

Data Index: 36866 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.2408. Min Act: -0.0001

Data Index: 1470046 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 3.5024. Min Range: -3.5024

Max Act: 2.1026. Min Act: -0.0000

Data Index: 1459430 (Python Code)

Max Activating Token Index: 451