Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1355 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.2446. Min Act: -0.0001
Data Index: 22409 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.1075. Min Act: -0.0001
Data Index: 1346993 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.2451. Min Act: -0.0001
Data Index: 1389739 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.1737. Min Act: -0.0001
Data Index: 1350456 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.1611. Min Act: -0.0001
Data Index: 488642 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.1715. Min Act: -0.0001
Data Index: 1096045 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9691. Min Act: -0.0001
Data Index: 1723424 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0593. Min Act: -0.0001
Data Index: 915612 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0659. Min Act: -0.0001
Data Index: 1787957 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0344. Min Act: -0.0001
Data Index: 881265 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0007. Min Act: -0.0001
Data Index: 28766 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9720. Min Act: -0.0001
Data Index: 575423 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9208. Min Act: -0.0001
Data Index: 755190 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0153. Min Act: -0.0001
Data Index: 284809 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9603. Min Act: -0.0001
Data Index: 270348 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9726. Min Act: -0.0001
Data Index: 381583 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.8957. Min Act: -0.0001
Data Index: 1755950 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9875. Min Act: -0.0001
Data Index: 847537 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2451. Min Range: -1.2451
Max Act: 0.9612. Min Act: -0.0001
Data Index: 1044271 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2451. Min Range: -1.2451
Max Act: 1.0005. Min Act: -0.0001
Data Index: 1894810 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19