Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0004

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0866. Min Act: -0.0004

Data Index: 1134797 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0862. Min Act: -0.0004

Data Index: 1055633 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0810. Min Act: -0.0004

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1321409 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0781. Min Act: -0.0004

Data Index: 854240 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0826. Min Act: -0.0004

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0807. Min Act: -0.0004

Data Index: 325573 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0813. Min Act: -0.0004

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0815. Min Act: -0.0004

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0792. Min Act: -0.0004

Data Index: 1284648 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0811. Min Act: -0.0004

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0807. Min Act: -0.0005

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0774. Min Act: -0.0004

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0772. Min Act: -0.0004

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0782. Min Act: -0.0004

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0793. Min Act: -0.0004

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0719. Min Act: -0.0004

Data Index: 243296 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0792. Min Act: -0.0004

Data Index: 1152946 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0783. Min Act: -0.0004

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 429