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

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

Neuron 577 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: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0005

Data Index: 242790 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0005

Data Index: 105911 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0463. Min Act: -0.0005

Data Index: 977319 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1198856 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0455. Min Act: -0.0005

Data Index: 499991 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0442. Min Act: -0.0005

Data Index: 1095755 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0422. Min Act: -0.0005

Data Index: 789786 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0430. Min Act: -0.0005

Data Index: 612768 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0437. Min Act: -0.0005

Data Index: 1174594 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1231029 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0438. Min Act: -0.0005

Data Index: 1053803 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0435. Min Act: -0.0005

Data Index: 1259655 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0424. Min Act: -0.0005

Data Index: 877171 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0405. Min Act: -0.0005

Data Index: 669206 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0436. Min Act: -0.0005

Data Index: 460550 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0429. Min Act: -0.0005

Data Index: 874471 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0404. Min Act: -0.0005

Data Index: 406537 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0403. Min Act: -0.0005

Data Index: 913591 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1056769 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0411. Min Act: -0.0005

Data Index: 521380 (C4 (Web Text))

Max Activating Token Index: 256