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

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

Neuron 5228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.7654. Min Act: -0.0000

Data Index: 955986 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1419998 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1473737 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1307782 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1370288 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2704. Min Act: -0.0000

Data Index: 302890 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3019. Min Act: -0.0000

Data Index: 839637 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.4371. Min Act: -0.0000

Data Index: 1450543 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1337894 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1405537 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1953. Min Act: -0.0000

Data Index: 662670 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1575452 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1477944 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1639881 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1505993 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1424197 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1496877 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1595200 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1635233 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1388. Min Act: -0.0000

Data Index: 978797 (C4 (Web Text))

Max Activating Token Index: 76