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

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

Neuron 537 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 899042 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1306169 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0691. Min Act: -0.0002

Data Index: 108204 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0699. Min Act: -0.0002

Data Index: 462703 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0685. Min Act: -0.0002

Data Index: 197299 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0645. Min Act: -0.0002

Data Index: 486130 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0643. Min Act: -0.0002

Data Index: 320553 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0640. Min Act: -0.0002

Data Index: 767789 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1092113 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0622. Min Act: -0.0002

Data Index: 263085 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1202720 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0621. Min Act: -0.0002

Data Index: 376114 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1642546 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1079292 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0605. Min Act: -0.0002

Data Index: 924021 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1095447 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1474176 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1337115 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0576. Min Act: -0.0002

Data Index: 756945 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1162986 (C4 (Web Text))

Max Activating Token Index: 696