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

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

Neuron 21 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2472. Min Range: -3.2472

Max Act: 3.2472. Min Act: -0.0000

Data Index: 1552862 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.9943. Min Act: -0.0000

Data Index: 1644673 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 3.2472. Min Range: -3.2472

Max Act: 3.0321. Min Act: -0.0000

Data Index: 1401255 (Python Code)

Max Activating Token Index: 156

Text #3

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.8019. Min Act: -0.0000

Data Index: 1648024 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.9584. Min Act: -0.0000

Data Index: 1592882 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.6558. Min Act: -0.0000

Data Index: 1551106 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.6335. Min Act: -0.0000

Data Index: 1607668 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.7305. Min Act: -0.0000

Data Index: 1394777 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.8509. Min Act: -0.0000

Data Index: 1412643 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.5350. Min Act: -0.0000

Data Index: 1385674 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.6267. Min Act: -0.0000

Data Index: 1593145 (Python Code)

Max Activating Token Index: 684

Text #11

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.2491. Min Act: -0.0000

Data Index: 1571778 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1426856 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.4163. Min Act: -0.0000

Data Index: 1601935 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.6634. Min Act: -0.0000

Data Index: 1492676 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.3951. Min Act: -0.0000

Data Index: 1642432 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.6345. Min Act: -0.0000

Data Index: 1581797 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.5060. Min Act: -0.0000

Data Index: 1644087 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.3581. Min Act: -0.0000

Data Index: 1442871 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 3.2472. Min Range: -3.2472

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1643966 (Python Code)

Max Activating Token Index: 826