Model: None
Dataset: The Pile
Neuron 1686 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.6786. Min Act: -0.1700
Data Index: 4583759 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.6630. Min Act: -0.1700
Data Index: 10708563 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.5534. Min Act: -0.1700
Data Index: 6692108 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.5064. Min Act: -0.1700
Data Index: 3028 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4907. Min Act: -0.1700
Data Index: 6666272 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4751. Min Act: -0.1700
Data Index: 2494032 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4751. Min Act: -0.1700
Data Index: 4754660 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4751. Min Act: -0.1700
Data Index: 8136984 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4594. Min Act: -0.1700
Data Index: 9947789 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4594. Min Act: -0.1700
Data Index: 9437695 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4437. Min Act: -0.1700
Data Index: 2894417 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4280. Min Act: -0.1700
Data Index: 2229901 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4280. Min Act: -0.1700
Data Index: 9166104 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4280. Min Act: -0.1700
Data Index: 7900464 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4280. Min Act: -0.1700
Data Index: 3439948 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4280. Min Act: -0.1700
Data Index: 3183738 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4124. Min Act: -0.1700
Data Index: 6154520 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4124. Min Act: -0.1700
Data Index: 2572597 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4124. Min Act: -0.1700
Data Index: 2572255 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6786. Min Range: -3.6786
Max Act: 3.4124. Min Act: -0.1700
Data Index: 815189 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19