Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2023 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0837. Min Act: -0.0003

Data Index: 544417 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0880. Min Act: -0.0003

Data Index: 364642 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0869. Min Act: -0.0003

Data Index: 719534 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1261592 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0003

Data Index: 249027 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1249438 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0824. Min Act: -0.0003

Data Index: 850599 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0847. Min Act: -0.0003

Data Index: 300574 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0797. Min Act: -0.0003

Data Index: 1051237 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0836. Min Act: -0.0003

Data Index: 808801 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1359345 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0788. Min Act: -0.0003

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0772. Min Act: -0.0003

Data Index: 878573 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0801. Min Act: -0.0003

Data Index: 958056 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0775. Min Act: -0.0003

Data Index: 183154 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0836. Min Act: -0.0003

Data Index: 435112 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0740. Min Act: -0.0003

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0786. Min Act: -0.0003

Data Index: 1030618 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0785. Min Act: -0.0004

Data Index: 703521 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0767. Min Act: -0.0003

Data Index: 536394 (C4 (Web Text))

Max Activating Token Index: 33