Model: None
Dataset: The Pile
Neuron 3405 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7991. Min Act: -0.1700
Data Index: 2085885 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7991. Min Act: -0.1700
Data Index: 4952645 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7832. Min Act: -0.1700
Data Index: 6971927 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7672. Min Act: -0.1700
Data Index: 9968256 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7353. Min Act: -0.1700
Data Index: 315220 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7193. Min Act: -0.1700
Data Index: 10343917 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7193. Min Act: -0.1700
Data Index: 2751923 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7033. Min Act: -0.1700
Data Index: 7333645 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7033. Min Act: -0.1699
Data Index: 7597693 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7033. Min Act: -0.1700
Data Index: 8756371 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.7033. Min Act: -0.1700
Data Index: 5697662 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6873. Min Act: -0.1700
Data Index: 3416202 (The Pile)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6873. Min Act: -0.1700
Data Index: 5499066 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6873. Min Act: -0.1700
Data Index: 6166884 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6873. Min Act: -0.1700
Data Index: 820010 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6713. Min Act: -0.1700
Data Index: 3106051 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6713. Min Act: -0.1700
Data Index: 3080269 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6713. Min Act: -0.1700
Data Index: 3848465 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6713. Min Act: -0.1700
Data Index: 4832271 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7991. Min Range: -2.7991
Max Act: 2.6713. Min Act: -0.1700
Data Index: 6970917 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19