Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1378135 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1409175 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1434938 (Python Code)

Max Activating Token Index: 688

Text #3

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1498293 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1648219 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1362315 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1409951 (Python Code)

Max Activating Token Index: 850

Text #7

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1435175 (Python Code)

Max Activating Token Index: 759

Text #8

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1454205 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1414981 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1646525 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1474934 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1592859 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1460794 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1544441 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1645645 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1574132 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1618080 (Python Code)

Max Activating Token Index: 747

Text #18

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1653066 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1656557 (Python Code)

Max Activating Token Index: 22