Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 3481596 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5228892 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 326616 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.1100. Min Act: -0.1700
Data Index: 390552 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.0788. Min Act: -0.1700
Data Index: 4528781 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1725. Min Range: -5.1725
Max Act: 5.0788. Min Act: -0.1700
Data Index: 4898313 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5401574 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9538. Min Act: -0.1700
Data Index: 2839428 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9538. Min Act: -0.1700
Data Index: 6812237 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9850. Min Act: -0.1700
Data Index: 6932477 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9538. Min Act: -0.1700
Data Index: 8763311 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5814358 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3685666 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9225. Min Act: -0.1700
Data Index: 4133476 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.8913. Min Act: -0.1700
Data Index: 764520 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9225. Min Act: -0.1700
Data Index: 2480465 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9225. Min Act: -0.1700
Data Index: 3879269 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.9225. Min Act: -0.1700
Data Index: 2027234 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.8913. Min Act: -0.1700
Data Index: 1704647 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1725. Min Range: -5.1725
Max Act: 4.8913. Min Act: -0.1700
Data Index: 3879265 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19