Model: None
Dataset: The Pile
Neuron 757 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.2561. Min Act: -0.1700
Data Index: 2100146 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.2561. Min Act: -0.1700
Data Index: 4409939 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.2247. Min Act: -0.1700
Data Index: 7061649 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1775. Min Act: -0.1700
Data Index: 2591333 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1775. Min Act: -0.1700
Data Index: 9563619 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1618. Min Act: -0.1700
Data Index: 5878684 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1460. Min Act: -0.1700
Data Index: 6314720 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1303. Min Act: -0.1700
Data Index: 5000179 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1303. Min Act: -0.1700
Data Index: 4317670 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1303. Min Act: -0.1700
Data Index: 7743017 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1303. Min Act: -0.1700
Data Index: 777437 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1145. Min Act: -0.1700
Data Index: 1114991 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.1145. Min Act: -0.1700
Data Index: 8578908 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 5266838 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 8679835 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 7568002 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 8663460 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 6503785 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0987. Min Act: -0.1700
Data Index: 1209149 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2561. Min Range: -3.2561
Max Act: 3.0830. Min Act: -0.1700
Data Index: 322588 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19