Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3457. Min Range: -7.3457
Max Act: 7.3457. Min Act: -0.1700
Data Index: 2870110 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3457. Min Range: -7.3457
Max Act: 7.1894. Min Act: -0.1700
Data Index: 358066 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3457. Min Range: -7.3457
Max Act: 7.1582. Min Act: -0.1700
Data Index: 1444277 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3457. Min Range: -7.3457
Max Act: 7.0332. Min Act: -0.1700
Data Index: 7333785 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9707. Min Act: -0.1700
Data Index: 3094675 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9707. Min Act: -0.1700
Data Index: 4089188 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9707. Min Act: -0.1700
Data Index: 560023 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9707. Min Act: -0.1700
Data Index: 2006933 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9707. Min Act: -0.1700
Data Index: 2945392 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.9082. Min Act: -0.1700
Data Index: 3349559 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8457. Min Act: -0.1700
Data Index: 388131 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8769. Min Act: -0.1700
Data Index: 5782717 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8457. Min Act: -0.1700
Data Index: 7434231 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8144. Min Act: -0.1700
Data Index: 660851 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8144. Min Act: -0.1700
Data Index: 6211742 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.8144. Min Act: -0.1700
Data Index: 6197757 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.7832. Min Act: -0.1700
Data Index: 8192108 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.7832. Min Act: -0.1700
Data Index: 1513413 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.7207. Min Act: -0.1700
Data Index: 2191192 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3457. Min Range: -7.3457
Max Act: 6.7519. Min Act: -0.1700
Data Index: 4224509 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19