Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0370. Min Range: -5.0370
Max Act: 5.0370. Min Act: -0.1700
Data Index: 634155 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7558. Min Act: -0.1700
Data Index: 1760579 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7245. Min Act: -0.1700
Data Index: 7496066 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6620. Min Act: -0.1700
Data Index: 1738264 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6308. Min Act: -0.1700
Data Index: 8201503 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6308. Min Act: -0.1700
Data Index: 423011 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.5995. Min Act: -0.1700
Data Index: 4291655 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.5683. Min Act: -0.1700
Data Index: 6197605 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.5683. Min Act: -0.1700
Data Index: 4118724 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.5058. Min Act: -0.1700
Data Index: 5500049 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.5058. Min Act: -0.1700
Data Index: 6890036 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4745. Min Act: -0.1700
Data Index: 7321037 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4745. Min Act: -0.1700
Data Index: 6120436 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7172192 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4745. Min Act: -0.1700
Data Index: 7254186 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4432. Min Act: -0.1700
Data Index: 4219183 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4745. Min Act: -0.1700
Data Index: 4429281 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4745. Min Act: -0.1700
Data Index: 1702537 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4432. Min Act: -0.1700
Data Index: 692889 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.4120. Min Act: -0.1700
Data Index: 7823594 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19