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

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

Neuron 4256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2631. Min Act: -0.0002

Data Index: 943570 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2270. Min Act: -0.0002

Data Index: 272945 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2496. Min Act: -0.0002

Data Index: 727753 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2176. Min Act: -0.0002

Data Index: 1579165 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2129. Min Act: -0.0002

Data Index: 32876 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2024. Min Act: -0.0002

Data Index: 345735 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2249. Min Act: -0.0002

Data Index: 1348713 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2009. Min Act: -0.0002

Data Index: 728990 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2208. Min Act: -0.0002

Data Index: 1324924 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2105. Min Act: -0.0002

Data Index: 224646 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2217. Min Act: -0.0002

Data Index: 133852 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1956. Min Act: -0.0002

Data Index: 375928 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2037. Min Act: -0.0002

Data Index: 91755 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1512. Min Act: -0.0002

Data Index: 2763 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2317. Min Act: -0.0002

Data Index: 1225953 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2046. Min Act: -0.0002

Data Index: 512438 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2204. Min Act: -0.0002

Data Index: 247376 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1941. Min Act: -0.0002

Data Index: 1220130 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1993. Min Act: -0.0002

Data Index: 271465 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1202527 (C4 (Web Text))

Max Activating Token Index: 459