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

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

Neuron 281 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: 1.1019. Min Range: -1.1019

Max Act: 1.1019. Min Act: -0.0000

Data Index: 674178 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0744. Min Act: -0.0000

Data Index: 213754 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0843. Min Act: -0.0000

Data Index: 308320 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1320040 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0887. Min Act: -0.0000

Data Index: 356530 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9583. Min Act: -0.0000

Data Index: 100700 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9558. Min Act: -0.0000

Data Index: 660552 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8856. Min Act: -0.0000

Data Index: 199996 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8903. Min Act: -0.0000

Data Index: 447876 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9749. Min Act: -0.0000

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8782. Min Act: -0.0000

Data Index: 457111 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8594. Min Act: -0.0000

Data Index: 429594 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1139596 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8208. Min Act: -0.0000

Data Index: 344050 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8464. Min Act: -0.0000

Data Index: 961686 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8860. Min Act: -0.0000

Data Index: 946481 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1169556 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8554. Min Act: -0.0000

Data Index: 340713 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1359279 (C4 (Web Text))

Max Activating Token Index: 1012