Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1258 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1429056 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0003

Data Index: 1640917 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0935. Min Act: -0.0004

Data Index: 1362736 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1647932 (Python Code)

Max Activating Token Index: 922

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1540874 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1555257 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1625890 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1566547 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1512349 (Python Code)

Max Activating Token Index: 953

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1375129 (Python Code)

Max Activating Token Index: 129

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1372320 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1563317 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1490338 (Python Code)

Max Activating Token Index: 422

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0877. Min Act: -0.0003

Data Index: 1487534 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1605300 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1362744 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1647271 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1361776 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1564575 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1414061 (Python Code)

Max Activating Token Index: 744