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

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

Neuron 1622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3520. Min Act: -0.0001

Data Index: 411093 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2276. Min Act: -0.0001

Data Index: 112890 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2305. Min Act: -0.0001

Data Index: 701566 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2129. Min Act: -0.0001

Data Index: 88547 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1283994 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1318905 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2002. Min Act: -0.0001

Data Index: 929979 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1150074 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1321425 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1952. Min Act: -0.0001

Data Index: 800128 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1986. Min Act: -0.0001

Data Index: 538354 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1854. Min Act: -0.0001

Data Index: 229047 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1330417 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1974. Min Act: -0.0001

Data Index: 151824 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1950. Min Act: -0.0001

Data Index: 94129 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1355387 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1079384 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1860. Min Act: -0.0001

Data Index: 847491 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1878. Min Act: -0.0001

Data Index: 11653 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.1907. Min Act: -0.0001

Data Index: 722744 (C4 (Web Text))

Max Activating Token Index: 241