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

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

Neuron 5141 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: 1.7892. Min Range: -1.7892

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1433680 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1603519 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7879. Min Act: -0.0000

Data Index: 1631582 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1392846 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3009. Min Act: -0.0000

Data Index: 221964 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5421. Min Act: -0.0000

Data Index: 150368 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1536307 (Python Code)

Max Activating Token Index: 317

Text #7

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1540946 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1640473 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1122656 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1613696 (Python Code)

Max Activating Token Index: 848

Text #11

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1563577 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1493261 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1394042 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1446124 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1110302 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1599890 (Python Code)

Max Activating Token Index: 993

Text #17

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1534277 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1498157 (Python Code)

Max Activating Token Index: 727

Text #19

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.1962. Min Act: -0.0000

Data Index: 454570 (C4 (Web Text))

Max Activating Token Index: 343