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

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

Neuron 5317 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4592. Min Act: -0.0000

Data Index: 1580986 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.5123. Min Act: -0.0000

Data Index: 1539727 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4891. Min Act: -0.0000

Data Index: 1493481 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4246. Min Act: -0.0000

Data Index: 1588357 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.0890. Min Act: -0.0000

Data Index: 1635798 (Python Code)

Max Activating Token Index: 932

Text #5

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.0616. Min Act: -0.0000

Data Index: 1490724 (Python Code)

Max Activating Token Index: 531

Text #6

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.9755. Min Act: -0.0000

Data Index: 1411253 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1497358 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.6229. Min Act: -0.0000

Data Index: 1455139 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.4106. Min Act: -0.0000

Data Index: 1450212 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.3865. Min Act: -0.0000

Data Index: 1503050 (Python Code)

Max Activating Token Index: 161

Text #11

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.3814. Min Act: -0.0000

Data Index: 1531642 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.5862. Min Act: -0.0000

Data Index: 1643721 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.4584. Min Act: -0.0000

Data Index: 1446605 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.6534. Min Act: -0.0000

Data Index: 1363448 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.3686. Min Act: -0.0000

Data Index: 48977 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.2230. Min Act: -0.0000

Data Index: 1614966 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1610660 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.0641. Min Act: -0.0000

Data Index: 840327 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 3.5123. Min Range: -3.5123

Max Act: 2.2110. Min Act: -0.0000

Data Index: 1483567 (Python Code)

Max Activating Token Index: 638