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

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

Neuron 1586 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: 4.2836. Min Range: -4.2836

Max Act: 4.2836. Min Act: -0.0000

Data Index: 980663 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.8733. Min Act: -0.0000

Data Index: 1061407 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 4.2836. Min Range: -4.2836

Max Act: 4.0012. Min Act: -0.0000

Data Index: 1087609 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.9985. Min Act: -0.0000

Data Index: 1061843 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.9860. Min Act: -0.0000

Data Index: 616670 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.9367. Min Act: -0.0000

Data Index: 1432048 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.8373. Min Act: -0.0000

Data Index: 1200195 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.8111. Min Act: -0.0000

Data Index: 1410085 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.7774. Min Act: -0.0000

Data Index: 1381176 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.6387. Min Act: -0.0000

Data Index: 1013985 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.5257. Min Act: -0.0000

Data Index: 343213 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.5136. Min Act: -0.0000

Data Index: 542643 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.0471. Min Act: -0.0000

Data Index: 816128 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.0307. Min Act: -0.0000

Data Index: 1213331 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.3280. Min Act: -0.0000

Data Index: 1238081 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1396345 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.2992. Min Act: -0.0000

Data Index: 1498877 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.2752. Min Act: -0.0000

Data Index: 964221 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.2598. Min Act: -0.0000

Data Index: 1410192 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 4.2836. Min Range: -4.2836

Max Act: 3.1287. Min Act: -0.0000

Data Index: 1439276 (Python Code)

Max Activating Token Index: 381