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

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

Neuron 3848 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.7908. Min Act: -0.0000

Data Index: 1469668 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.6474. Min Act: -0.0000

Data Index: 1622511 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.6165. Min Act: -0.0000

Data Index: 1408979 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.5468. Min Act: -0.0000

Data Index: 1400208 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1457271 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3089. Min Act: -0.0000

Data Index: 1560988 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.6494. Min Act: -0.0000

Data Index: 1400326 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3537. Min Act: -0.0000

Data Index: 1453257 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1534811 (Python Code)

Max Activating Token Index: 914

Text #9

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1591456 (Python Code)

Max Activating Token Index: 680

Text #10

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1640295 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3463. Min Act: -0.0000

Data Index: 1493798 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1589172 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.5500. Min Act: -0.0000

Data Index: 1397464 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.3077. Min Act: -0.0000

Data Index: 1393898 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.2867. Min Act: -0.0000

Data Index: 1564293 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1458132 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.2387. Min Act: -0.0000

Data Index: 1607241 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.2443. Min Act: -0.0000

Data Index: 1490170 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 2.7908. Min Range: -2.7908

Max Act: 2.2098. Min Act: -0.0000

Data Index: 1424196 (Python Code)

Max Activating Token Index: 868