Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2596 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0468. Min Act: -0.0002
Data Index: 659909 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0444. Min Act: -0.0002
Data Index: 1916232 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0442. Min Act: -0.0002
Data Index: 1678932 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0414. Min Act: -0.0002
Data Index: 936874 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0384. Min Act: -0.0002
Data Index: 1491298 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0372. Min Act: -0.0002
Data Index: 632431 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0367. Min Act: -0.0002
Data Index: 1508029 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0355. Min Act: -0.0002
Data Index: 1701221 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0348. Min Act: -0.0002
Data Index: 458011 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0355. Min Act: -0.0002
Data Index: 79324 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0332. Min Act: -0.0002
Data Index: 524890 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0331. Min Act: -0.0002
Data Index: 1996640 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0331. Min Act: -0.0002
Data Index: 1673638 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0335. Min Act: -0.0002
Data Index: 288373 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0321. Min Act: -0.0002
Data Index: 886552 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0326. Min Act: -0.0002
Data Index: 820024 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0316. Min Act: -0.0003
Data Index: 1754501 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0316. Min Act: -0.0003
Data Index: 459523 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0329. Min Act: -0.0002
Data Index: 133790 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0468. Min Range: -0.0468
Max Act: 0.0317. Min Act: -0.0002
Data Index: 496071 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19