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

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

Neuron 2004 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.9004. Min Act: -0.0003

Data Index: 602954 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8186. Min Act: -0.0002

Data Index: 914608 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8372. Min Act: -0.0002

Data Index: 760117 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8448. Min Act: -0.0002

Data Index: 228290 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8193. Min Act: -0.0003

Data Index: 880394 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7784. Min Act: -0.0002

Data Index: 712248 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7436. Min Act: -0.0003

Data Index: 581340 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7164. Min Act: -0.0002

Data Index: 1118100 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7609. Min Act: -0.0003

Data Index: 810301 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7296. Min Act: -0.0002

Data Index: 1322291 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6996. Min Act: -0.0002

Data Index: 633457 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6961. Min Act: -0.0003

Data Index: 990469 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6940. Min Act: -0.0003

Data Index: 309383 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6847. Min Act: -0.0003

Data Index: 1195298 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6868. Min Act: -0.0003

Data Index: 54962 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6519. Min Act: -0.0002

Data Index: 1206282 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7129. Min Act: -0.0003

Data Index: 1330214 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6640. Min Act: -0.0003

Data Index: 1068053 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6529. Min Act: -0.0003

Data Index: 227969 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6541. Min Act: -0.0003

Data Index: 1129784 (C4 (Web Text))

Max Activating Token Index: 145