Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1569 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2175. Min Act: -0.0000

Data Index: 700994 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2134. Min Act: -0.0000

Data Index: 197438 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2112. Min Act: -0.0000

Data Index: 27491 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2064. Min Act: -0.0000

Data Index: 253541 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2067. Min Act: -0.0000

Data Index: 841198 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1123943 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2001. Min Act: -0.0000

Data Index: 922094 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2013. Min Act: -0.0000

Data Index: 796082 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1910. Min Act: -0.0000

Data Index: 426636 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1284589 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1955. Min Act: -0.0000

Data Index: 733981 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1358818 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1952. Min Act: -0.0000

Data Index: 329309 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1073428 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1924. Min Act: -0.0000

Data Index: 372496 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2141. Min Act: -0.0000

Data Index: 749787 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2062. Min Act: -0.0000

Data Index: 177663 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1920. Min Act: -0.0000

Data Index: 313303 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1774. Min Act: -0.0000

Data Index: 895661 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1945. Min Act: -0.0000

Data Index: 665252 (C4 (Web Text))

Max Activating Token Index: 394