Model: None
Dataset: The Pile
Neuron 87 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.0507. Min Range: -3.0507
Max Act: 3.0507. Min Act: -0.1700
Data Index: 266736 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0507. Min Range: -3.0507
Max Act: 3.0349. Min Act: -0.1700
Data Index: 8816475 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0507. Min Range: -3.0507
Max Act: 3.0191. Min Act: -0.1700
Data Index: 4142797 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0507. Min Range: -3.0507
Max Act: 3.0033. Min Act: -0.1700
Data Index: 8492819 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9875. Min Act: -0.1700
Data Index: 8641304 (The Pile)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9875. Min Act: -0.1700
Data Index: 4277777 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9875. Min Act: -0.1700
Data Index: 7492993 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9875. Min Act: -0.1700
Data Index: 2557099 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9717. Min Act: -0.1700
Data Index: 1641478 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9559. Min Act: -0.1700
Data Index: 6594722 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9559. Min Act: -0.1700
Data Index: 4167564 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 2803580 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 745444 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 5328889 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 7450643 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 10525604 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 4227818 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 7270841 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9400. Min Act: -0.1700
Data Index: 1526378 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9242. Min Act: -0.1700
Data Index: 8299332 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19