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

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

Neuron 4119 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1618006 (Python Code)

Max Activating Token Index: 763

Text #1

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.8672. Min Act: -0.0000

Data Index: 1404759 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7669. Min Act: -0.0000

Data Index: 1436024 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6575. Min Act: -0.0000

Data Index: 1553929 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7436. Min Act: -0.0000

Data Index: 1529653 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7458. Min Act: -0.0000

Data Index: 1604935 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1511799 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1483239 (Python Code)

Max Activating Token Index: 395

Text #8

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1632671 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1626250 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7587. Min Act: -0.0000

Data Index: 1512358 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6533. Min Act: -0.0000

Data Index: 1389960 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5436. Min Act: -0.0001

Data Index: 1465854 (Python Code)

Max Activating Token Index: 698

Text #13

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1451639 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5831. Min Act: -0.0000

Data Index: 1624128 (Python Code)

Max Activating Token Index: 322

Text #15

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6232. Min Act: -0.0000

Data Index: 1574602 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1363369 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1584610 (Python Code)

Max Activating Token Index: 678

Text #18

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1423000 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 1.9024. Min Range: -1.9024

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1483876 (Python Code)

Max Activating Token Index: 356