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

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

Neuron 2186 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: 1.0964. Min Range: -1.0964

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1587721 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 1.0964. Min Range: -1.0964

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1578994 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1546794 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 1.0964. Min Range: -1.0964

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1502517 (Python Code)

Max Activating Token Index: 82

Text #4

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1486249 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1592246 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1462839 (Python Code)

Max Activating Token Index: 850

Text #7

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1501534 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1494379 (Python Code)

Max Activating Token Index: 393

Text #9

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1627930 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1400560 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1370272 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9218. Min Act: -0.0000

Data Index: 803067 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9137. Min Act: -0.0000

Data Index: 304064 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1475912 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1405561 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1483442 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1364299 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1628738 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1404171 (Python Code)

Max Activating Token Index: 1012