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

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

Neuron 1618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2286. Min Act: -0.0001

Data Index: 613447 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0001

Data Index: 120897 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2255. Min Act: -0.0001

Data Index: 125458 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2058. Min Act: -0.0001

Data Index: 467753 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1033650 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2092. Min Act: -0.0001

Data Index: 421905 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2009. Min Act: -0.0001

Data Index: 527567 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1952. Min Act: -0.0001

Data Index: 561538 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1131201 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2003. Min Act: -0.0001

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1792. Min Act: -0.0001

Data Index: 619938 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1832. Min Act: -0.0001

Data Index: 1070184 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1077139 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1023014 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1856. Min Act: -0.0001

Data Index: 723009 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1311561 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1909. Min Act: -0.0001

Data Index: 126348 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1200776 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1241243 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1953. Min Act: -0.0001

Data Index: 913492 (C4 (Web Text))

Max Activating Token Index: 809