Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 979 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0574. Min Act: -0.0002
Data Index: 827462 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0574. Min Act: -0.0002
Data Index: 458960 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0574. Min Act: -0.0002
Data Index: 943955 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0574. Min Act: -0.0002
Data Index: 497243 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0574. Min Act: -0.0002
Data Index: 1260321 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0338. Min Act: -0.0002
Data Index: 1855040 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0338. Min Act: -0.0002
Data Index: 256313 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0322. Min Act: -0.0002
Data Index: 876129 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0322. Min Act: -0.0002
Data Index: 711208 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0308. Min Act: -0.0003
Data Index: 68737 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0294. Min Act: -0.0003
Data Index: 1325011 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0278. Min Act: -0.0002
Data Index: 343578 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0278. Min Act: -0.0002
Data Index: 32004 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0278. Min Act: -0.0002
Data Index: 1439616 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0278. Min Act: -0.0002
Data Index: 493803 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0278. Min Act: -0.0002
Data Index: 206776 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0271. Min Act: -0.0002
Data Index: 1616107 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0269. Min Act: -0.0002
Data Index: 1559475 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0269. Min Act: -0.0002
Data Index: 608221 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0574. Min Range: -0.0574
Max Act: 0.0269. Min Act: -0.0002
Data Index: 1106617 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19