Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0003

Data Index: 555667 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1171. Min Act: -0.0003

Data Index: 270254 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1146. Min Act: -0.0003

Data Index: 302655 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1077. Min Act: -0.0003

Data Index: 1210570 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1067. Min Act: -0.0003

Data Index: 165960 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1049. Min Act: -0.0003

Data Index: 898499 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1060. Min Act: -0.0003

Data Index: 1177045 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1049. Min Act: -0.0004

Data Index: 978481 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1050. Min Act: -0.0004

Data Index: 830056 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1351304 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1020. Min Act: -0.0003

Data Index: 493039 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0934. Min Act: -0.0003

Data Index: 857887 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0988. Min Act: -0.0004

Data Index: 375774 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0965. Min Act: -0.0003

Data Index: 1004307 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0985. Min Act: -0.0003

Data Index: 14440 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0986. Min Act: -0.0003

Data Index: 1158395 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0974. Min Act: -0.0004

Data Index: 567947 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0961. Min Act: -0.0003

Data Index: 198240 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1186445 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0938. Min Act: -0.0004

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 975