Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1710 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0844. Min Act: -0.0001

Data Index: 1100100 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0603. Min Act: -0.0001

Data Index: 989121 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.8853. Min Act: -0.0001

Data Index: 976404 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.9640. Min Act: -0.0001

Data Index: 396510 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.9143. Min Act: -0.0001

Data Index: 761516 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0495. Min Act: -0.0001

Data Index: 235851 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0276. Min Act: -0.0001

Data Index: 567966 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0107. Min Act: -0.0001

Data Index: 767921 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0015. Min Act: -0.0001

Data Index: 1139486 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.1145. Min Act: -0.0001

Data Index: 390673 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0930. Min Act: -0.0001

Data Index: 1308457 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.9607. Min Act: -0.0001

Data Index: 446118 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.7665. Min Act: -0.0001

Data Index: 244527 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.6359. Min Act: -0.0001

Data Index: 697317 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.1145. Min Range: -3.1145

Max Act: 3.0294. Min Act: -0.0001

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.8358. Min Act: -0.0001

Data Index: 1354648 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.7019. Min Act: -0.0001

Data Index: 122765 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.6613. Min Act: -0.0001

Data Index: 657153 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.6454. Min Act: -0.0001

Data Index: 176514 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.1145. Min Range: -3.1145

Max Act: 2.3975. Min Act: -0.0001

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 297