Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 66 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2695. Min Range: -1.2695

Max Act: 1.2695. Min Act: -0.0001

Data Index: 1571892 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 1.2695. Min Range: -1.2695

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1629464 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 1.2695. Min Range: -1.2695

Max Act: 1.2277. Min Act: -0.0001

Data Index: 1627963 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1538477 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9498. Min Act: 0.0000

Data Index: 1625631 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9215. Min Act: -0.0001

Data Index: 1437295 (Python Code)

Max Activating Token Index: 689

Text #6

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1610137 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9086. Min Act: -0.0001

Data Index: 1563796 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.9624. Min Act: -0.0001

Data Index: 1563805 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8876. Min Act: -0.0001

Data Index: 1455263 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1462438 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1619971 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8279. Min Act: -0.0001

Data Index: 1523521 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1420527 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8097. Min Act: -0.0001

Data Index: 1578680 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1641770 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.7979. Min Act: -0.0000

Data Index: 261392 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1367918 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1545659 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 1.2695. Min Range: -1.2695

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1609576 (Python Code)

Max Activating Token Index: 990