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

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

Neuron 5849 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1500225 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1356314 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6245. Min Act: -0.0000

Data Index: 548295 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5955. Min Act: -0.0000

Data Index: 524105 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6302. Min Act: -0.0000

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1591250 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1163800 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1030179 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1217303 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6122. Min Act: -0.0000

Data Index: 628135 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1652021 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6159. Min Act: -0.0000

Data Index: 993246 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1429830 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6319. Min Act: -0.0000

Data Index: 779275 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5515. Min Act: -0.0000

Data Index: 652572 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5746. Min Act: -0.0000

Data Index: 623321 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1007469 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1081267 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5732. Min Act: -0.0000

Data Index: 826120 (C4 (Web Text))

Max Activating Token Index: 553