Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4195 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1367309 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1525508 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1474183 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1458782 (Python Code)

Max Activating Token Index: 826

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1393233 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1435707 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1447003 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1389185 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1402980 (Python Code)

Max Activating Token Index: 592

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1593859 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1603316 (Python Code)

Max Activating Token Index: 307

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1468765 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1651114 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1633118 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1568734 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1509847 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1438014 (Python Code)

Max Activating Token Index: 899

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1504113 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1418584 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1632478 (Python Code)

Max Activating Token Index: 404