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

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

Neuron 68 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0969. Min Act: -0.0002

Data Index: 138946 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1307300 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0864. Min Act: -0.0002

Data Index: 31121 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0843. Min Act: -0.0002

Data Index: 501538 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0842. Min Act: -0.0002

Data Index: 200813 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1091028 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1174909 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0821. Min Act: -0.0002

Data Index: 163531 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1348510 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0772. Min Act: -0.0002

Data Index: 484044 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0857. Min Act: -0.0002

Data Index: 793236 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0754. Min Act: -0.0002

Data Index: 674912 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0734. Min Act: -0.0002

Data Index: 425240 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0734. Min Act: -0.0002

Data Index: 458271 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1202015 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1083764 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1111498 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0697. Min Act: -0.0002

Data Index: 793553 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0748. Min Act: -0.0002

Data Index: 582863 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0717. Min Act: -0.0002

Data Index: 996672 (C4 (Web Text))

Max Activating Token Index: 553