Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 945 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 4.3641. Min Range: -4.3641
Max Act: 4.3641. Min Act: -0.0001
Data Index: 872591 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.8089. Min Act: -0.0002
Data Index: 1366179 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.5407. Min Act: -0.0001
Data Index: 813626 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.2785. Min Act: -0.0001
Data Index: 1000654 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.8546. Min Act: -0.0001
Data Index: 1220306 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.6181. Min Act: -0.0001
Data Index: 757980 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.0163. Min Act: -0.0001
Data Index: 1662362 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.9894. Min Act: -0.0001
Data Index: 428949 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.5724. Min Act: -0.0001
Data Index: 143136 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.1197. Min Act: -0.0001
Data Index: 446778 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.6011. Min Act: -0.0001
Data Index: 1972911 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3641. Min Range: -4.3641
Max Act: 3.3849. Min Act: -0.0001
Data Index: 179053 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.4829. Min Act: -0.0001
Data Index: 1246651 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.5987. Min Act: -0.0001
Data Index: 1228662 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.4168. Min Act: -0.0001
Data Index: 8988 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.3629. Min Act: -0.0001
Data Index: 1832655 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.1671. Min Act: -0.0001
Data Index: 698282 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.4100. Min Act: -0.0001
Data Index: 1704399 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3641. Min Range: -4.3641
Max Act: 2.2125. Min Act: -0.0001
Data Index: 790299 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3641. Min Range: -4.3641
Max Act: 1.8906. Min Act: -0.0001
Data Index: 1841178 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19