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

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

Neuron 4753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1510796 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1415506 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1418476 (Python Code)

Max Activating Token Index: 912

Text #3

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1488838 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1401656 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1637234 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1362295 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1650523 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1605912 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1426894 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1485528 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1370311 (Python Code)

Max Activating Token Index: 831

Text #12

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1601454 (Python Code)

Max Activating Token Index: 320

Text #13

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1638340 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1543170 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1653756 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1560950 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7738. Min Act: -0.0000

Data Index: 793377 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1452729 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1436769 (Python Code)

Max Activating Token Index: 18