Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5118 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1047453 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0669. Min Act: -0.0000

Data Index: 544798 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0640. Min Act: -0.0000

Data Index: 327635 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0640. Min Act: -0.0000

Data Index: 412896 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0591. Min Act: -0.0000

Data Index: 890982 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0666. Min Act: -0.0000

Data Index: 774034 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0565. Min Act: -0.0000

Data Index: 502611 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1323608 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0557. Min Act: -0.0000

Data Index: 19176 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1165470 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0563. Min Act: -0.0000

Data Index: 951495 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1226698 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0464. Min Act: -0.0000

Data Index: 61303 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0518. Min Act: -0.0000

Data Index: 429132 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0502. Min Act: -0.0000

Data Index: 71277 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1002968 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0456. Min Act: -0.0000

Data Index: 769935 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1418718 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0445. Min Act: -0.0000

Data Index: 709452 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0407. Min Act: -0.0000

Data Index: 413996 (C4 (Web Text))

Max Activating Token Index: 855