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

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

Neuron 1346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5665. Min Range: -2.5665

Max Act: 2.5665. Min Act: -0.0000

Data Index: 1490445 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 2.5665. Min Range: -2.5665

Max Act: 2.1641. Min Act: -0.0000

Data Index: 1528347 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.7004. Min Act: -0.0000

Data Index: 1422828 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.7865. Min Act: -0.0000

Data Index: 1405185 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.6146. Min Act: -0.0000

Data Index: 1577699 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1656015 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.8609. Min Act: -0.0000

Data Index: 1444834 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1441781 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1527955 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1609604 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1609372 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1496955 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.4093. Min Act: -0.0000

Data Index: 1539020 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1581968 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1501405 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1518349 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1636418 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1386382 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1499475 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 2.5665. Min Range: -2.5665

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1472746 (Python Code)

Max Activating Token Index: 429