Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1132. Min Range: -13.1132
Max Act: 13.1132. Min Act: -0.1700
Data Index: 3951560 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1132. Min Range: -13.1132
Max Act: 13.0507. Min Act: -0.1700
Data Index: 7313914 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.9882. Min Act: -0.1700
Data Index: 7313913 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1132. Min Range: -13.1132
Max Act: 13.0507. Min Act: -0.1700
Data Index: 8481543 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.9882. Min Act: -0.1700
Data Index: 6089357 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.8632. Min Act: -0.1700
Data Index: 4640781 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.8632. Min Act: -0.1700
Data Index: 1056467 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.8632. Min Act: -0.1700
Data Index: 8729852 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.7382. Min Act: -0.1700
Data Index: 263400 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.7382. Min Act: -0.1700
Data Index: 749803 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.7382. Min Act: -0.1700
Data Index: 5596897 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.7382. Min Act: -0.1700
Data Index: 81391 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 5393972 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 4623954 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 3531577 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 4565368 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 4649966 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 1466410 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1696
Data Index: 6043421 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1132. Min Range: -13.1132
Max Act: 12.6757. Min Act: -0.1700
Data Index: 3933085 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19