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

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

Neuron 327 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: 0.1187. Min Range: -0.1187

Max Act: 0.1128. Min Act: -0.0002

Data Index: 595853 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 300809 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1110127 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0952. Min Act: -0.0002

Data Index: 27669 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1003. Min Act: -0.0002

Data Index: 544347 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1331111 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0947. Min Act: -0.0002

Data Index: 834512 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0884. Min Act: -0.0002

Data Index: 921206 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0908. Min Act: -0.0002

Data Index: 494104 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0893. Min Act: -0.0002

Data Index: 641338 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0815. Min Act: -0.0002

Data Index: 91768 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0781. Min Act: -0.0002

Data Index: 261817 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0797. Min Act: -0.0002

Data Index: 455093 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0805. Min Act: -0.0002

Data Index: 55411 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1205318 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0722. Min Act: -0.0002

Data Index: 503961 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0720. Min Act: -0.0002

Data Index: 553490 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0707. Min Act: -0.0002

Data Index: 361176 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1062030 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1295223 (C4 (Web Text))

Max Activating Token Index: 47