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

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

Neuron 950 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: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0003

Data Index: 309856 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0866. Min Act: -0.0002

Data Index: 315422 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0867. Min Act: -0.0002

Data Index: 697941 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0849. Min Act: -0.0002

Data Index: 823593 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0831. Min Act: -0.0002

Data Index: 495662 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1112056 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0842. Min Act: -0.0002

Data Index: 936215 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0818. Min Act: -0.0002

Data Index: 310143 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0811. Min Act: -0.0002

Data Index: 979518 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0828. Min Act: -0.0002

Data Index: 55332 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0813. Min Act: -0.0002

Data Index: 895940 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0812. Min Act: -0.0002

Data Index: 519600 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0818. Min Act: -0.0002

Data Index: 212104 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1265927 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0796. Min Act: -0.0002

Data Index: 493400 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0809. Min Act: -0.0002

Data Index: 313920 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0800. Min Act: -0.0002

Data Index: 643873 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0801. Min Act: -0.0002

Data Index: 926589 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0796. Min Act: -0.0002

Data Index: 39983 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0777. Min Act: -0.0002

Data Index: 927915 (C4 (Web Text))

Max Activating Token Index: 362