Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1456 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1246966 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2062. Min Act: -0.0002

Data Index: 914240 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2048. Min Act: -0.0002

Data Index: 1064812 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1952. Min Act: -0.0002

Data Index: 1362453 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1937. Min Act: -0.0002

Data Index: 532251 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2017. Min Act: -0.0001

Data Index: 474612 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1343118 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1878. Min Act: -0.0002

Data Index: 1425816 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1930. Min Act: -0.0001

Data Index: 845276 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1854. Min Act: -0.0002

Data Index: 1214255 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1939. Min Act: -0.0001

Data Index: 680846 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1113052 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1244463 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1809. Min Act: -0.0002

Data Index: 79190 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1891. Min Act: -0.0001

Data Index: 540433 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1935. Min Act: -0.0002

Data Index: 219522 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1303063 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1339534 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1881. Min Act: -0.0001

Data Index: 214048 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2011. Min Act: -0.0002

Data Index: 253357 (C4 (Web Text))

Max Activating Token Index: 840