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

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

Neuron 5110 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: 0.9214. Min Range: -0.9214

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1370858 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8946. Min Act: -0.0000

Data Index: 359411 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1189301 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1121162 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1305653 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1585284 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7963. Min Act: -0.0000

Data Index: 471421 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7890. Min Act: -0.0000

Data Index: 359331 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1266572 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7808. Min Act: -0.0000

Data Index: 431059 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1249902 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7155. Min Act: -0.0000

Data Index: 816293 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6985. Min Act: -0.0000

Data Index: 146272 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6711. Min Act: -0.0000

Data Index: 664090 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6985. Min Act: -0.0000

Data Index: 936828 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7105. Min Act: -0.0000

Data Index: 920656 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1403545 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1596957 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.6968. Min Act: -0.0000

Data Index: 480729 (C4 (Web Text))

Max Activating Token Index: 252