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

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

Neuron 895 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0005

Data Index: 816453 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0462. Min Act: -0.0005

Data Index: 1168965 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0458. Min Act: -0.0005

Data Index: 1226436 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0458. Min Act: -0.0005

Data Index: 830783 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0444. Min Act: -0.0005

Data Index: 411746 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0409. Min Act: -0.0005

Data Index: 723198 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0414. Min Act: -0.0005

Data Index: 1027040 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0421. Min Act: -0.0005

Data Index: 189367 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0417. Min Act: -0.0005

Data Index: 1135262 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0418. Min Act: -0.0005

Data Index: 355041 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0404. Min Act: -0.0005

Data Index: 954621 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0389. Min Act: -0.0005

Data Index: 834751 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0424. Min Act: -0.0005

Data Index: 549096 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0387. Min Act: -0.0005

Data Index: 917955 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0400. Min Act: -0.0005

Data Index: 433519 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0423. Min Act: -0.0005

Data Index: 498482 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0410. Min Act: -0.0005

Data Index: 447838 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1281938 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0399. Min Act: -0.0005

Data Index: 876889 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0387. Min Act: -0.0005

Data Index: 427882 (C4 (Web Text))

Max Activating Token Index: 433