Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3088 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0001

Data Index: 941389 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0837. Min Act: -0.0001

Data Index: 184619 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1205854 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0808. Min Act: -0.0002

Data Index: 250298 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1062926 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0813. Min Act: -0.0001

Data Index: 720062 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0812. Min Act: -0.0001

Data Index: 294794 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0809. Min Act: -0.0002

Data Index: 936642 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0796. Min Act: -0.0002

Data Index: 733360 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1005456 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0825. Min Act: -0.0001

Data Index: 90011 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0792. Min Act: -0.0002

Data Index: 200993 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0822. Min Act: -0.0002

Data Index: 325652 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1107152 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0816. Min Act: -0.0002

Data Index: 65219 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0783. Min Act: -0.0001

Data Index: 408238 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0780. Min Act: -0.0002

Data Index: 918815 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0774. Min Act: -0.0001

Data Index: 117147 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1043532 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1029997 (C4 (Web Text))

Max Activating Token Index: 680