Model: None
Dataset: The Pile
Neuron 3954 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 1497 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 6121 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 22340 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 21448 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 20745 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 3850 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 6542 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 19365 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 6050 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 17834 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 7216 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 2913 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 13353 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 9441 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 8992 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 4269 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 3496 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 6131 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 8872 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7535. Min Range: -1.7535
Max Act: 1.7535. Min Act: -0.1700
Data Index: 8628 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19