Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0855. Min Range: -6.0855
Max Act: 6.0855. Min Act: -0.1700
Data Index: 2835014 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0855. Min Range: -6.0855
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5557851 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.9605. Min Act: -0.1700
Data Index: 6721048 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.9293. Min Act: -0.1700
Data Index: 4099770 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.9293. Min Act: -0.1700
Data Index: 7411322 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.8668. Min Act: -0.1700
Data Index: 7046827 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.8668. Min Act: -0.1700
Data Index: 7681400 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.8355. Min Act: -0.1700
Data Index: 5736211 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.8043. Min Act: -0.1700
Data Index: 3673135 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.8043. Min Act: -0.1700
Data Index: 3212984 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.7730. Min Act: -0.1700
Data Index: 1676727 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.7730. Min Act: -0.1700
Data Index: 585501 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.7418. Min Act: -0.1700
Data Index: 30666 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.7105. Min Act: -0.1700
Data Index: 207567 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.7105. Min Act: -0.1700
Data Index: 2735345 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.6793. Min Act: -0.1700
Data Index: 8165611 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.6793. Min Act: -0.1700
Data Index: 3085292 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.6793. Min Act: -0.1700
Data Index: 7388949 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.6793. Min Act: -0.1700
Data Index: 6273154 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0855. Min Range: -6.0855
Max Act: 5.6793. Min Act: -0.1700
Data Index: 692180 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19