Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 959 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0001

Data Index: 493922 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1027. Min Act: -0.0001

Data Index: 558814 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0931. Min Act: -0.0001

Data Index: 885477 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0945. Min Act: -0.0001

Data Index: 456377 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0930. Min Act: -0.0002

Data Index: 957600 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0908. Min Act: -0.0002

Data Index: 504562 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0920. Min Act: -0.0001

Data Index: 620723 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0916. Min Act: -0.0001

Data Index: 108943 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0885. Min Act: -0.0001

Data Index: 52172 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1301672 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0875. Min Act: -0.0002

Data Index: 376270 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1299561 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1026514 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0871. Min Act: -0.0001

Data Index: 40057 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0864. Min Act: -0.0001

Data Index: 625340 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1078342 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0830. Min Act: -0.0001

Data Index: 846688 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1036557 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1260514 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0847. Min Act: -0.0002

Data Index: 244616 (C4 (Web Text))

Max Activating Token Index: 802