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

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

Neuron 3168 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1405248 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1369548 (Python Code)

Max Activating Token Index: 859

Text #2

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1404229 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1557976 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1456369 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1600495 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1607740 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1371258 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1445691 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1518060 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1602182 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1529324 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1598434 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1419439 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1485703 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1524991 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1583988 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0673. Min Act: -0.0000

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1419517 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1372039 (Python Code)

Max Activating Token Index: 679