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

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

Neuron 148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1069097 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0792. Min Act: -0.0002

Data Index: 366939 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1272186 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1166731 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0724. Min Act: -0.0001

Data Index: 92694 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0579. Min Act: -0.0001

Data Index: 159651 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1261892 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0635. Min Act: -0.0001

Data Index: 466154 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0659. Min Act: -0.0001

Data Index: 40366 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0675. Min Act: -0.0002

Data Index: 725787 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1172407 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0620. Min Act: -0.0002

Data Index: 112959 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0641. Min Act: -0.0001

Data Index: 202032 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1150410 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0591. Min Act: -0.0001

Data Index: 546065 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0583. Min Act: -0.0002

Data Index: 108764 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1042431 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0644. Min Act: -0.0002

Data Index: 181815 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0594. Min Act: -0.0002

Data Index: 479379 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0555. Min Act: -0.0002

Data Index: 701269 (C4 (Web Text))

Max Activating Token Index: 775