Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3906 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0632. Min Range: -8.0632
Max Act: 8.0632. Min Act: -0.1700
Data Index: 5677714 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0632. Min Range: -8.0632
Max Act: 8.0007. Min Act: -0.1700
Data Index: 6189193 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.9382. Min Act: -0.1700
Data Index: 2846022 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.8757. Min Act: -0.1700
Data Index: 1344491 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.7507. Min Act: -0.1700
Data Index: 1741451 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.7507. Min Act: -0.1700
Data Index: 8002357 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.6882. Min Act: -0.1700
Data Index: 4852753 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.6569. Min Act: -0.1700
Data Index: 3742826 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.5632. Min Act: -0.1700
Data Index: 4150430 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.5007. Min Act: -0.1700
Data Index: 8705787 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4694. Min Act: -0.1700
Data Index: 336514 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4694. Min Act: -0.1700
Data Index: 7763047 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4382. Min Act: -0.1700
Data Index: 3305479 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4382. Min Act: -0.1700
Data Index: 4286478 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4382. Min Act: -0.1700
Data Index: 7962238 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4069. Min Act: -0.1700
Data Index: 6961275 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.4069. Min Act: -0.1700
Data Index: 567647 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.3757. Min Act: -0.1700
Data Index: 3798588 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.3132. Min Act: -0.1700
Data Index: 4565336 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0632. Min Range: -8.0632
Max Act: 7.3132. Min Act: -0.1700
Data Index: 5306688 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19