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

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

Neuron 97 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: 1.7211. Min Range: -1.7211

Max Act: 1.7211. Min Act: -0.0000

Data Index: 175296 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.5818. Min Act: -0.0000

Data Index: 335008 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.6907. Min Act: -0.0000

Data Index: 326462 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1219660 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.6130. Min Act: -0.0000

Data Index: 456054 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.5790. Min Act: -0.0000

Data Index: 844434 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.3772. Min Act: -0.0001

Data Index: 494937 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.4558. Min Act: -0.0000

Data Index: 625575 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.4186. Min Act: -0.0000

Data Index: 250850 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1236471 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.5737. Min Act: -0.0000

Data Index: 385984 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.3958. Min Act: -0.0000

Data Index: 261325 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1231825 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.3768. Min Act: -0.0000

Data Index: 142516 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.4437. Min Act: -0.0000

Data Index: 940385 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1297564 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.3097. Min Act: -0.0000

Data Index: 408346 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.2986. Min Act: -0.0000

Data Index: 181496 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.2908. Min Act: -0.0001

Data Index: 1109808 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.7211. Min Range: -1.7211

Max Act: 1.1404. Min Act: -0.0000

Data Index: 558426 (C4 (Web Text))

Max Activating Token Index: 1003