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

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

Neuron 1404 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.3791. Min Act: -0.0000

Data Index: 874240 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.2032. Min Act: -0.0000

Data Index: 972025 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1357690 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0545. Min Act: -0.0000

Data Index: 940827 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.1617. Min Act: -0.0000

Data Index: 954052 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0717. Min Act: -0.0000

Data Index: 461140 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.1754. Min Act: -0.0000

Data Index: 1277091 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9875. Min Act: -0.0000

Data Index: 8560 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9087. Min Act: -0.0000

Data Index: 749024 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9464. Min Act: -0.0000

Data Index: 1288481 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1300740 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0148. Min Act: -0.0000

Data Index: 1214705 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9530. Min Act: -0.0000

Data Index: 887620 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9098. Min Act: -0.0000

Data Index: 490158 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0072. Min Act: -0.0000

Data Index: 170906 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0990. Min Act: -0.0001

Data Index: 893896 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.3791. Min Range: -2.3791

Max Act: 2.0327. Min Act: -0.0000

Data Index: 1229284 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1155352 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9204. Min Act: -0.0001

Data Index: 209950 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 2.3791. Min Range: -2.3791

Max Act: 1.9918. Min Act: -0.0001

Data Index: 1100987 (C4 (Web Text))

Max Activating Token Index: 553