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

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

Neuron 1746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2371. Min Act: -0.0005

Data Index: 330584 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2073. Min Act: -0.0005

Data Index: 546572 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2142. Min Act: -0.0005

Data Index: 963216 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2063. Min Act: -0.0005

Data Index: 315441 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1980. Min Act: -0.0005

Data Index: 279525 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2072. Min Act: -0.0005

Data Index: 1023678 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2118. Min Act: -0.0005

Data Index: 642959 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2117. Min Act: -0.0005

Data Index: 987004 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2121. Min Act: -0.0005

Data Index: 673861 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2145. Min Act: -0.0005

Data Index: 729201 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1770. Min Act: -0.0005

Data Index: 182752 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2036. Min Act: -0.0005

Data Index: 863533 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1956. Min Act: -0.0005

Data Index: 1238343 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1940. Min Act: -0.0005

Data Index: 34112 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2021. Min Act: -0.0005

Data Index: 286482 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1866. Min Act: -0.0005

Data Index: 1272796 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1922. Min Act: -0.0005

Data Index: 1292165 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1881. Min Act: -0.0005

Data Index: 1192571 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1991. Min Act: -0.0005

Data Index: 1267324 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1910. Min Act: -0.0005

Data Index: 878669 (C4 (Web Text))

Max Activating Token Index: 214