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

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

Neuron 1409 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1271346 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.2015. Min Act: -0.0000

Data Index: 1135587 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1495570 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.2187. Min Act: -0.0000

Data Index: 1604465 (Python Code)

Max Activating Token Index: 1017

Text #4

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.2403. Min Act: -0.0000

Data Index: 142803 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.2406. Min Act: -0.0000

Data Index: 311826 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.1485. Min Act: -0.0000

Data Index: 178891 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.0250. Min Act: -0.0000

Data Index: 307162 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.8853. Min Act: -0.0000

Data Index: 184324 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.9298. Min Act: -0.0000

Data Index: 1402944 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.9242. Min Act: -0.0000

Data Index: 406468 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1402227 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 2.5752. Min Range: -2.5752

Max Act: 2.0048. Min Act: -0.0000

Data Index: 58223 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1562801 (Python Code)

Max Activating Token Index: 862

Text #14

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.8292. Min Act: -0.0000

Data Index: 670887 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.7774. Min Act: -0.0000

Data Index: 936400 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.8076. Min Act: -0.0000

Data Index: 570931 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.7686. Min Act: -0.0000

Data Index: 629441 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1114270 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 2.5752. Min Range: -2.5752

Max Act: 1.7862. Min Act: -0.0000

Data Index: 388057 (C4 (Web Text))

Max Activating Token Index: 619