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

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

Neuron 1846 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: 0.9240. Min Range: -0.9240

Max Act: 0.9240. Min Act: -0.0000

Data Index: 312756 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.8023. Min Act: -0.0000

Data Index: 647448 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7598. Min Act: -0.0000

Data Index: 352022 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7743. Min Act: -0.0000

Data Index: 496301 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.7183. Min Act: -0.0000

Data Index: 737359 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6988. Min Act: -0.0000

Data Index: 584982 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6482. Min Act: -0.0000

Data Index: 788494 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6759. Min Act: -0.0000

Data Index: 373079 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6489. Min Act: -0.0000

Data Index: 42466 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6435. Min Act: -0.0000

Data Index: 797530 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6887. Min Act: -0.0000

Data Index: 415887 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6006. Min Act: -0.0000

Data Index: 787748 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6402. Min Act: -0.0000

Data Index: 24032 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1184536 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5758. Min Act: -0.0000

Data Index: 543645 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.6349. Min Act: -0.0000

Data Index: 897227 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1235880 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1122220 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1161480 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.9240. Min Range: -0.9240

Max Act: 0.5710. Min Act: -0.0000

Data Index: 957748 (C4 (Web Text))

Max Activating Token Index: 558