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

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

Neuron 1637 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: 0.3824. Min Range: -0.3824

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1480391 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1627038 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1578462 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1458279 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1451165 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1609271 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1389689 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1591213 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1634680 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1633827 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1458044 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1533709 (Python Code)

Max Activating Token Index: 293

Text #12

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1415516 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1427124 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1617101 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1635232 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1391865 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1605085 (Python Code)

Max Activating Token Index: 157

Text #18

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1412673 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1625535 (Python Code)

Max Activating Token Index: 820