Model: None
Dataset: The Pile
Neuron 3356 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3960. Min Act: -0.1700
Data Index: 9757232 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3960. Min Act: -0.1700
Data Index: 1249580 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3797. Min Act: -0.1700
Data Index: 3589057 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3306. Min Act: -0.1700
Data Index: 9049196 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3306. Min Act: -0.1700
Data Index: 6164421 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.3306. Min Act: -0.1700
Data Index: 5681201 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2977. Min Act: -0.1700
Data Index: 2635504 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2813. Min Act: -0.1700
Data Index: 9649442 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2648. Min Act: -0.1700
Data Index: 2160234 (The Pile)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2648. Min Act: -0.1700
Data Index: 6453844 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2648. Min Act: -0.1700
Data Index: 9915290 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2648. Min Act: -0.1700
Data Index: 3956453 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2648. Min Act: -0.1700
Data Index: 10285964 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 4259623 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 10483290 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 5627819 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 3811702 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 5196120 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2483. Min Act: -0.1700
Data Index: 3926957 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3960. Min Range: -2.3960
Max Act: 2.2318. Min Act: -0.1700
Data Index: 2127439 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19