Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1052 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0064. Min Range: -2.0064
Max Act: 2.0064. Min Act: -0.0000
Data Index: 145674 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.9697. Min Act: -0.0000
Data Index: 1178904 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.7881. Min Act: -0.0000
Data Index: 1653983 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.6178. Min Act: -0.0000
Data Index: 786085 (The Pile)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5591. Min Act: 0.0000
Data Index: 1992333 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5640. Min Act: 0.0000
Data Index: 72931 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.6271. Min Act: 0.0000
Data Index: 678780 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.7197. Min Act: 0.0000
Data Index: 436299 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5804. Min Act: -0.0000
Data Index: 221122 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5784. Min Act: -0.0000
Data Index: 1796804 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5651. Min Act: -0.0000
Data Index: 885536 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5474. Min Act: 0.0000
Data Index: 1242912 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.4846. Min Act: -0.0000
Data Index: 803043 (The Pile)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.4732. Min Act: -0.0000
Data Index: 1354011 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.4655. Min Act: 0.0000
Data Index: 338544 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.5478. Min Act: 0.0000
Data Index: 1918615 (The Pile)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.4392. Min Act: -0.0000
Data Index: 1637882 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.3883. Min Act: 0.0000
Data Index: 1162537 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.3818. Min Act: 0.0000
Data Index: 465462 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0064. Min Range: -2.0064
Max Act: 1.3100. Min Act: -0.0000
Data Index: 952814 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19