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

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

Neuron 4801 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1355349 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1131606 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0002

Data Index: 152974 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0531. Min Act: -0.0002

Data Index: 554641 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0531. Min Act: -0.0002

Data Index: 793655 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0522. Min Act: -0.0002

Data Index: 255874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0519. Min Act: -0.0003

Data Index: 158641 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0516. Min Act: -0.0003

Data Index: 947440 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1261648 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0520. Min Act: -0.0003

Data Index: 593550 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0515. Min Act: -0.0003

Data Index: 62975 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0518. Min Act: -0.0003

Data Index: 720485 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0524. Min Act: -0.0002

Data Index: 966456 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1023173 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0505. Min Act: -0.0002

Data Index: 771901 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1082609 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0503. Min Act: -0.0002

Data Index: 413568 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0504. Min Act: -0.0002

Data Index: 106272 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0498. Min Act: -0.0002

Data Index: 512981 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0496. Min Act: -0.0002

Data Index: 699435 (C4 (Web Text))

Max Activating Token Index: 655