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

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

Neuron 1631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0003

Data Index: 988438 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0985. Min Act: -0.0003

Data Index: 309320 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1040. Min Act: -0.0003

Data Index: 658771 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0963. Min Act: -0.0003

Data Index: 555140 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0961. Min Act: -0.0003

Data Index: 484320 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0872. Min Act: -0.0003

Data Index: 385785 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0878. Min Act: -0.0003

Data Index: 725835 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0902. Min Act: -0.0003

Data Index: 234840 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1206957 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0822. Min Act: -0.0003

Data Index: 80052 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1204601 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0880. Min Act: -0.0003

Data Index: 56004 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1061312 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0877. Min Act: -0.0003

Data Index: 361831 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0871. Min Act: -0.0003

Data Index: 981050 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0866. Min Act: -0.0003

Data Index: 208996 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1163251 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1170432 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1240660 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0789. Min Act: -0.0003

Data Index: 969142 (C4 (Web Text))

Max Activating Token Index: 964