Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.3008. Min Act: -0.1700
Data Index: 2600267 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.3008. Min Act: -0.1700
Data Index: 6325610 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.2071. Min Act: -0.1700
Data Index: 4289721 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.2071. Min Act: -0.1700
Data Index: 2359775 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.1446. Min Act: -0.1700
Data Index: 6981597 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0821. Min Act: -0.1700
Data Index: 5299777 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0196. Min Act: -0.1700
Data Index: 6025725 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0196. Min Act: -0.1700
Data Index: 4327602 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0196. Min Act: -0.1700
Data Index: 714976 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0196. Min Act: -0.1700
Data Index: 242782 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3008. Min Range: -6.3008
Max Act: 6.0508. Min Act: -0.1700
Data Index: 5114167 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9883. Min Act: -0.1700
Data Index: 8066816 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9883. Min Act: -0.1700
Data Index: 614251 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9883. Min Act: -0.1700
Data Index: 5728006 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2230919 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2660309 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2663339 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.8946. Min Act: -0.1700
Data Index: 1358103 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.8946. Min Act: -0.1700
Data Index: 4603080 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3008. Min Range: -6.3008
Max Act: 5.8946. Min Act: -0.1700
Data Index: 3062995 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19