Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2181 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3619. Min Act: -0.0001

Data Index: 172679 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1183866 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3163. Min Act: -0.0001

Data Index: 148870 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2872. Min Act: -0.0001

Data Index: 253967 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1166003 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2961. Min Act: -0.0001

Data Index: 215119 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1048119 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2904. Min Act: -0.0001

Data Index: 181460 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1121017 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1327653 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2584. Min Act: -0.0001

Data Index: 647641 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1177829 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1614196 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2837. Min Act: -0.0001

Data Index: 602624 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2736. Min Act: -0.0001

Data Index: 556622 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2912. Min Act: -0.0001

Data Index: 781144 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2732. Min Act: -0.0001

Data Index: 955525 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2694. Min Act: -0.0001

Data Index: 480619 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2767. Min Act: -0.0001

Data Index: 754332 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1438767 (Python Code)

Max Activating Token Index: 632