Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1037. Min Act: -0.0002

Data Index: 88864 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1067. Min Act: -0.0002

Data Index: 848771 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1001. Min Act: -0.0002

Data Index: 828227 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0931. Min Act: -0.0002

Data Index: 759320 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0934. Min Act: -0.0002

Data Index: 696443 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0870. Min Act: -0.0002

Data Index: 126031 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0863. Min Act: -0.0002

Data Index: 181427 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0822. Min Act: -0.0002

Data Index: 807357 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0850. Min Act: -0.0002

Data Index: 763380 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0842. Min Act: -0.0002

Data Index: 285724 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0836. Min Act: -0.0002

Data Index: 599688 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1294422 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0823. Min Act: -0.0002

Data Index: 878413 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0825. Min Act: -0.0002

Data Index: 37076 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1196778 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0786. Min Act: -0.0002

Data Index: 929739 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1332888 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0802. Min Act: -0.0002

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0808. Min Act: -0.0002

Data Index: 573458 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0803. Min Act: -0.0002

Data Index: 193701 (C4 (Web Text))

Max Activating Token Index: 553