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

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

Neuron 2340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2528. Min Range: -2.2528

Max Act: 2.2528. Min Act: -0.0000

Data Index: 194645 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.9964. Min Act: -0.0000

Data Index: 683214 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 2.2528. Min Range: -2.2528

Max Act: 2.1885. Min Act: -0.0000

Data Index: 1147381 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 2.2528. Min Range: -2.2528

Max Act: 2.1518. Min Act: -0.0000

Data Index: 405421 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.9714. Min Act: -0.0000

Data Index: 189933 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7595. Min Act: -0.0000

Data Index: 882278 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.9126. Min Act: -0.0000

Data Index: 936918 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7926. Min Act: -0.0000

Data Index: 37212 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.8789. Min Act: -0.0000

Data Index: 1298052 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.8607. Min Act: -0.0000

Data Index: 466529 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7624. Min Act: -0.0000

Data Index: 73170 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7479. Min Act: -0.0000

Data Index: 1046485 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.8413. Min Act: -0.0000

Data Index: 986483 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.8209. Min Act: -0.0000

Data Index: 888482 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.6988. Min Act: -0.0000

Data Index: 627965 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7864. Min Act: -0.0000

Data Index: 428930 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.8004. Min Act: -0.0000

Data Index: 1258554 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.7792. Min Act: -0.0000

Data Index: 827724 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.6233. Min Act: -0.0000

Data Index: 305655 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 2.2528. Min Range: -2.2528

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1010243 (C4 (Web Text))

Max Activating Token Index: 556