Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.2540. Min Act: -0.0001

Data Index: 76188 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.1338. Min Act: -0.0001

Data Index: 604489 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.0155. Min Act: -0.0000

Data Index: 569764 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.1452. Min Act: -0.0001

Data Index: 214321 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.0437. Min Act: -0.0001

Data Index: 341318 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.0324. Min Act: -0.0001

Data Index: 67644 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.0133. Min Act: -0.0001

Data Index: 832429 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1127648 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9244. Min Act: -0.0001

Data Index: 569487 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1509497 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1568396 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1652884 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 1.2540. Min Range: -1.2540

Max Act: 1.0283. Min Act: -0.0000

Data Index: 684516 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9810. Min Act: -0.0001

Data Index: 45746 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1084008 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1561112 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1458826 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1258399 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.8599. Min Act: -0.0001

Data Index: 1640499 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 1.2540. Min Range: -1.2540

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1397568 (Python Code)

Max Activating Token Index: 844