Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.9676. Min Range: -5.9676

Max Act: 5.9676. Min Act: -0.0000

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 5.9676. Min Range: -5.9676

Max Act: 5.6604. Min Act: -0.0000

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.6839. Min Act: -0.0000

Data Index: 501747 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.5733. Min Act: -0.0000

Data Index: 962994 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.5206. Min Act: -0.0000

Data Index: 1313219 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.4163. Min Act: -0.0000

Data Index: 939813 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.1731. Min Act: -0.0000

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.4180. Min Act: -0.0000

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.2010. Min Act: -0.0000

Data Index: 129660 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.9546. Min Act: -0.0000

Data Index: 619554 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.9094. Min Act: -0.0000

Data Index: 1033511 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.0122. Min Act: -0.0000

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.8225. Min Act: -0.0000

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.9079. Min Act: -0.0000

Data Index: 992582 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.8999. Min Act: -0.0000

Data Index: 1638663 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 5.9676. Min Range: -5.9676

Max Act: 4.0896. Min Act: -0.0000

Data Index: 1570162 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.9054. Min Act: -0.0000

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.8184. Min Act: -0.0000

Data Index: 1429044 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.7884. Min Act: -0.0000

Data Index: 1633580 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 5.9676. Min Range: -5.9676

Max Act: 3.7798. Min Act: -0.0000

Data Index: 1506743 (Python Code)

Max Activating Token Index: 44