Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0995. Min Range: -6.0995
Max Act: 6.0995. Min Act: -0.1700
Data Index: 2930906 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0995. Min Range: -6.0995
Max Act: 6.0370. Min Act: -0.1700
Data Index: 751839 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0995. Min Range: -6.0995
Max Act: 6.0057. Min Act: -0.1700
Data Index: 6718562 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.8807. Min Act: -0.1700
Data Index: 1189785 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7870. Min Act: -0.1700
Data Index: 7465869 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7557. Min Act: -0.1700
Data Index: 3359394 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7557. Min Act: -0.1700
Data Index: 8608105 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7245. Min Act: -0.1700
Data Index: 726217 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7245. Min Act: -0.1700
Data Index: 7703151 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7245. Min Act: -0.1700
Data Index: 3888688 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4776601 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.7245. Min Act: -0.1700
Data Index: 1106910 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6830085 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6932. Min Act: -0.1700
Data Index: 5644991 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6932. Min Act: -0.1700
Data Index: 742951 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6620. Min Act: -0.1700
Data Index: 3386315 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6620. Min Act: -0.1700
Data Index: 3404689 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6307. Min Act: -0.1700
Data Index: 5588610 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.6307. Min Act: -0.1700
Data Index: 1824635 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0995. Min Range: -6.0995
Max Act: 5.5682. Min Act: -0.1700
Data Index: 2207802 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19