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

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

Neuron 2408 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0139. Min Range: -1.0139

Max Act: 1.0139. Min Act: -0.0000

Data Index: 254799 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9029. Min Act: -0.0000

Data Index: 190776 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9376. Min Act: -0.0000

Data Index: 552292 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9279. Min Act: -0.0000

Data Index: 831936 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8365. Min Act: -0.0000

Data Index: 710472 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9119. Min Act: -0.0000

Data Index: 745610 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8116. Min Act: -0.0000

Data Index: 225396 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8073. Min Act: -0.0000

Data Index: 746595 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8425. Min Act: -0.0000

Data Index: 156832 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7912. Min Act: -0.0000

Data Index: 485530 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7746. Min Act: -0.0000

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7340. Min Act: -0.0000

Data Index: 625942 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8254. Min Act: -0.0000

Data Index: 461641 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6676. Min Act: -0.0000

Data Index: 704302 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7037. Min Act: -0.0000

Data Index: 618590 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6889. Min Act: -0.0000

Data Index: 426382 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7563. Min Act: -0.0000

Data Index: 851695 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6606. Min Act: -0.0000

Data Index: 865714 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6522. Min Act: -0.0000

Data Index: 965090 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1653098 (Python Code)

Max Activating Token Index: 90