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

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

Neuron 4304 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9599. Min Act: -0.0000

Data Index: 61115 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9595. Min Act: -0.0000

Data Index: 977802 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9691. Min Act: -0.0000

Data Index: 111032 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9202. Min Act: -0.0000

Data Index: 591509 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1058131 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1347442 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8970. Min Act: -0.0000

Data Index: 785021 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8162. Min Act: -0.0000

Data Index: 654992 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8724. Min Act: -0.0000

Data Index: 341376 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8419. Min Act: -0.0000

Data Index: 222047 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8428. Min Act: -0.0000

Data Index: 575058 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1056017 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8771. Min Act: -0.0000

Data Index: 833787 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7926. Min Act: -0.0000

Data Index: 86634 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1315574 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8016. Min Act: -0.0000

Data Index: 208655 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1342470 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1231316 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8269. Min Act: -0.0000

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7597. Min Act: -0.0000

Data Index: 418500 (C4 (Web Text))

Max Activating Token Index: 304