Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4740 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1910. Min Act: -0.1700
Data Index: 4705296 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1910. Min Act: -0.1700
Data Index: 6361811 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1285. Min Act: -0.1700
Data Index: 4086603 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1285. Min Act: -0.1700
Data Index: 5385254 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1285. Min Act: -0.1700
Data Index: 1902129 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1285. Min Act: -0.1700
Data Index: 3036782 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1285. Min Act: -0.1700
Data Index: 6671694 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0660. Min Act: -0.1700
Data Index: 4851543 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0660. Min Act: -0.1700
Data Index: 1050345 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0347. Min Act: -0.1700
Data Index: 658511 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0347. Min Act: -0.1700
Data Index: 7532752 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0035. Min Act: -0.1700
Data Index: 8365183 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0035. Min Act: -0.1700
Data Index: 371479 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 4509285 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 4478067 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5225203 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5449775 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 2521457 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9410. Min Act: -0.1700
Data Index: 8217160 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9410. Min Act: -0.1700
Data Index: 243080 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19