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

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

Neuron 3071 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1162665 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1303753 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2159. Min Act: -0.0000

Data Index: 383146 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2103. Min Act: -0.0000

Data Index: 238376 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2000. Min Act: -0.0000

Data Index: 777087 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1905. Min Act: -0.0000

Data Index: 867686 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2039. Min Act: -0.0000

Data Index: 62809 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1016141 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1997. Min Act: -0.0000

Data Index: 404937 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1907. Min Act: -0.0000

Data Index: 154787 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1926. Min Act: -0.0000

Data Index: 66025 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1945. Min Act: -0.0000

Data Index: 765701 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1139877 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1841. Min Act: -0.0000

Data Index: 94502 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1697. Min Act: -0.0000

Data Index: 336874 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1681. Min Act: -0.0000

Data Index: 736904 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1799. Min Act: -0.0000

Data Index: 187883 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1858. Min Act: -0.0000

Data Index: 280216 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1025006 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1807. Min Act: -0.0000

Data Index: 912253 (C4 (Web Text))

Max Activating Token Index: 573