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

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

Neuron 3146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.8003. Min Act: -0.0000

Data Index: 1496778 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1555994 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7684. Min Act: -0.0000

Data Index: 1484148 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1471969 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1622932 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1651830 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1528908 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1649916 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1647487 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1484371 (Python Code)

Max Activating Token Index: 450

Text #10

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1631883 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1375150 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6218. Min Act: -0.0000

Data Index: 1637220 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6613. Min Act: -0.0000

Data Index: 1403292 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1444830 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6963. Min Act: -0.0000

Data Index: 1607749 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6004. Min Act: -0.0000

Data Index: 1416784 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1408893 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1470967 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 1.8003. Min Range: -1.8003

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1524244 (Python Code)

Max Activating Token Index: 392