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

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

Neuron 823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.1011. Min Act: -0.0000

Data Index: 134405 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0996. Min Act: -0.0000

Data Index: 125463 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1232830 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0940. Min Act: -0.0000

Data Index: 726073 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0912. Min Act: -0.0000

Data Index: 397040 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0866. Min Act: -0.0000

Data Index: 373589 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0854. Min Act: -0.0000

Data Index: 669728 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0867. Min Act: -0.0000

Data Index: 513051 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0883. Min Act: -0.0000

Data Index: 952921 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1240479 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0849. Min Act: -0.0000

Data Index: 565954 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0856. Min Act: -0.0000

Data Index: 331223 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1048230 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0827. Min Act: -0.0000

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0816. Min Act: -0.0001

Data Index: 398718 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0840. Min Act: -0.0000

Data Index: 585845 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1352032 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0858. Min Act: -0.0001

Data Index: 353122 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0826. Min Act: -0.0000

Data Index: 721639 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0831. Min Act: -0.0000

Data Index: 912795 (C4 (Web Text))

Max Activating Token Index: 191