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

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

Neuron 2228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1245944 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0000

Data Index: 974936 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1030. Min Act: -0.0000

Data Index: 875657 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1142917 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1067. Min Act: -0.0001

Data Index: 382191 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0850. Min Act: -0.0001

Data Index: 628450 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0875. Min Act: -0.0001

Data Index: 192097 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0794. Min Act: -0.0001

Data Index: 244391 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0814. Min Act: -0.0001

Data Index: 639379 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0797. Min Act: -0.0001

Data Index: 889209 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0822. Min Act: -0.0001

Data Index: 817629 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1095177 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0785. Min Act: -0.0001

Data Index: 504608 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0802. Min Act: -0.0001

Data Index: 732043 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0751. Min Act: -0.0001

Data Index: 423077 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0774. Min Act: -0.0001

Data Index: 892321 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0777. Min Act: -0.0001

Data Index: 858018 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1124136 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0783. Min Act: -0.0001

Data Index: 795850 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0784. Min Act: -0.0001

Data Index: 356854 (C4 (Web Text))

Max Activating Token Index: 625