Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4069 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0002

Data Index: 171323 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1055. Min Act: -0.0002

Data Index: 614843 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0972. Min Act: -0.0002

Data Index: 158803 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0983. Min Act: -0.0002

Data Index: 398295 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1027951 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1325616 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1123652 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0839. Min Act: -0.0002

Data Index: 145089 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0767. Min Act: -0.0002

Data Index: 793648 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0793. Min Act: -0.0002

Data Index: 281700 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1265118 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0817. Min Act: -0.0002

Data Index: 680619 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0738. Min Act: -0.0002

Data Index: 153486 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1002904 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1301551 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0782. Min Act: -0.0002

Data Index: 843973 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0773. Min Act: -0.0002

Data Index: 326291 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1280238 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1310871 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0793. Min Act: -0.0002

Data Index: 317265 (C4 (Web Text))

Max Activating Token Index: 757