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

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

Neuron 3666 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0001

Data Index: 641997 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1617676 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1494812 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1610952 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1651624 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1536057 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1483087 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0468. Min Act: -0.0001

Data Index: 862966 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0434. Min Act: -0.0001

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1049400 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0460. Min Act: -0.0001

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1317523 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0420. Min Act: -0.0001

Data Index: 542257 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0433. Min Act: -0.0001

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0402. Min Act: -0.0001

Data Index: 607915 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1315035 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0408. Min Act: -0.0001

Data Index: 50121 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0422. Min Act: -0.0001

Data Index: 975353 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0368. Min Act: -0.0001

Data Index: 26870 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0400. Min Act: -0.0001

Data Index: 859680 (C4 (Web Text))

Max Activating Token Index: 782