Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 227 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0002

Data Index: 581336 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0704. Min Act: -0.0002

Data Index: 300955 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0743. Min Act: -0.0002

Data Index: 630096 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0650. Min Act: -0.0002

Data Index: 314324 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1246145 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0594. Min Act: -0.0002

Data Index: 48777 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1267075 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0636. Min Act: -0.0002

Data Index: 298618 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0627. Min Act: -0.0002

Data Index: 499065 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1310612 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1276168 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0574. Min Act: -0.0002

Data Index: 170654 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1134824 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0608. Min Act: -0.0002

Data Index: 998528 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1339208 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0518. Min Act: -0.0002

Data Index: 593498 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0536. Min Act: -0.0002

Data Index: 167226 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0513. Min Act: -0.0002

Data Index: 562307 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1092439 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0520. Min Act: -0.0002

Data Index: 929547 (C4 (Web Text))

Max Activating Token Index: 757