Model: None
Dataset: The Pile
Neuron 2015 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4957. Min Act: -0.1700
Data Index: 9988909 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4487. Min Act: -0.1700
Data Index: 5597399 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4643. Min Act: -0.1700
Data Index: 7377854 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4330. Min Act: -0.1700
Data Index: 4601396 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4487. Min Act: -0.1700
Data Index: 8014027 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4330. Min Act: -0.1700
Data Index: 4502479 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4173. Min Act: -0.1700
Data Index: 3222811 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4016. Min Act: -0.1700
Data Index: 4543062 (The Pile)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4330. Min Act: -0.1700
Data Index: 9323258 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4016. Min Act: -0.1700
Data Index: 2394293 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4016. Min Act: -0.1700
Data Index: 857485 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3859. Min Act: -0.1700
Data Index: 1628128 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4016. Min Act: -0.1700
Data Index: 6396170 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4016. Min Act: -0.1700
Data Index: 5443436 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3545. Min Act: -0.1700
Data Index: 9660455 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3702. Min Act: -0.1700
Data Index: 3779277 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3702. Min Act: -0.1700
Data Index: 6292391 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3702. Min Act: -0.1700
Data Index: 5990514 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3859. Min Act: -0.1700
Data Index: 2603526 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3859. Min Act: -0.1700
Data Index: 4110744 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19