Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2200 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1755. Min Range: -2.1755
Max Act: 2.1755. Min Act: -0.0000
Data Index: 1471363 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1755. Min Range: -2.1755
Max Act: 2.0418. Min Act: -0.0000
Data Index: 695499 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8668. Min Act: -0.0000
Data Index: 650433 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8282. Min Act: -0.0000
Data Index: 1829248 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.9380. Min Act: -0.0000
Data Index: 1102380 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1755. Min Range: -2.1755
Max Act: 2.0300. Min Act: -0.0001
Data Index: 1433561 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1755. Min Range: -2.1755
Max Act: 2.0177. Min Act: -0.0000
Data Index: 254591 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.7079. Min Act: -0.0000
Data Index: 1572983 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8916. Min Act: -0.0000
Data Index: 160715 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8927. Min Act: -0.0000
Data Index: 1021098 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.9785. Min Act: -0.0000
Data Index: 934717 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.7257. Min Act: -0.0000
Data Index: 1944713 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8212. Min Act: -0.0000
Data Index: 976826 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.7057. Min Act: -0.0000
Data Index: 1885774 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8072. Min Act: -0.0000
Data Index: 78824 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8693. Min Act: -0.0000
Data Index: 1404566 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.6476. Min Act: -0.0000
Data Index: 1761334 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.6504. Min Act: -0.0001
Data Index: 285829 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8017. Min Act: -0.0000
Data Index: 1078818 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1755. Min Range: -2.1755
Max Act: 1.8223. Min Act: -0.0000
Data Index: 1778881 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19