Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1402 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 1478647 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0124. Min Act: -0.1700
Data Index: 7658203 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7311. Min Act: -0.1700
Data Index: 8213002 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7311. Min Act: -0.1700
Data Index: 1645106 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7311. Min Act: -0.1700
Data Index: 4662807 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6686. Min Act: -0.1700
Data Index: 8318757 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6686. Min Act: -0.1700
Data Index: 8509128 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 5726915 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 8434730 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 1017489 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6061. Min Act: -0.1700
Data Index: 2177836 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 5714106 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2666424 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 4435258 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 6320275 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4502690 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8797730 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.4811. Min Act: -0.1700
Data Index: 539708 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 6845775 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.4811. Min Act: -0.1700
Data Index: 7692781 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19