Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5673 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0672. Min Act: -0.0001
Data Index: 918135 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0642. Min Act: -0.0001
Data Index: 1505263 (Python Code)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0539. Min Act: -0.0001
Data Index: 438417 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0568. Min Act: -0.0001
Data Index: 1114285 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0661. Min Act: -0.0001
Data Index: 680776 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0514. Min Act: -0.0001
Data Index: 315200 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0662. Min Act: -0.0001
Data Index: 1000031 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0587. Min Act: -0.0001
Data Index: 395857 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0547. Min Act: -0.0001
Data Index: 41578 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0513. Min Act: -0.0001
Data Index: 134773 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0546. Min Act: -0.0001
Data Index: 631187 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0446. Min Act: -0.0001
Data Index: 84446 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0583. Min Act: -0.0001
Data Index: 1572376 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0588. Min Act: -0.0001
Data Index: 860569 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0451. Min Act: -0.0001
Data Index: 1005229 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0502. Min Act: -0.0001
Data Index: 1239850 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0556. Min Act: -0.0001
Data Index: 1189592 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0553. Min Act: -0.0001
Data Index: 893885 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0551. Min Act: -0.0001
Data Index: 578748 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0672. Min Range: -0.0672
Max Act: 0.0428. Min Act: -0.0001
Data Index: 370351 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19