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

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

Neuron 4782 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: 0.0187. Min Range: -0.0187

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1407059 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0163. Min Act: -0.0002

Data Index: 363623 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0160. Min Act: -0.0003

Data Index: 297000 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0161. Min Act: -0.0003

Data Index: 975081 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1600310 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1339687 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0146. Min Act: -0.0003

Data Index: 919891 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1151966 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0142. Min Act: -0.0002

Data Index: 360961 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0170. Min Act: -0.0002

Data Index: 140584 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1130586 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0148. Min Act: -0.0002

Data Index: 470267 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0143. Min Act: -0.0002

Data Index: 356797 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1250316 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0134. Min Act: -0.0002

Data Index: 155580 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0134. Min Act: -0.0002

Data Index: 300043 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0145. Min Act: -0.0002

Data Index: 673632 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0135. Min Act: -0.0002

Data Index: 28344 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0130. Min Act: -0.0003

Data Index: 255516 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0135. Min Act: -0.0002

Data Index: 324441 (C4 (Web Text))

Max Activating Token Index: 462