Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1598 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.3822. Min Act: -0.0000
Data Index: 313933 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.4762. Min Act: -0.0000
Data Index: 28388 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.5916. Min Act: -0.0000
Data Index: 1199740 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1417. Min Act: -0.0000
Data Index: 896904 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.2556. Min Act: -0.0000
Data Index: 1174694 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.2980. Min Act: -0.0000
Data Index: 290747 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.2927. Min Act: -0.0000
Data Index: 1300705 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.2056. Min Act: 0.0000
Data Index: 1740214 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.3679. Min Act: -0.0000
Data Index: 1554804 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1648. Min Act: 0.0000
Data Index: 456825 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1365. Min Act: -0.0000
Data Index: 1656466 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1503. Min Act: -0.0000
Data Index: 1301715 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1528. Min Act: -0.0000
Data Index: 1823179 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.4875. Min Act: -0.0000
Data Index: 525175 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.0784. Min Act: -0.0000
Data Index: 673645 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.2155. Min Act: -0.0000
Data Index: 997209 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.0498. Min Act: -0.0000
Data Index: 909289 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.0152. Min Act: -0.0000
Data Index: 1253477 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.0763. Min Act: -0.0000
Data Index: 1473356 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5916. Min Range: -1.5916
Max Act: 1.1412. Min Act: -0.0000
Data Index: 1507971 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19