Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1798. Min Range: -6.1798
Max Act: 6.1798. Min Act: -0.1700
Data Index: 6031868 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1798. Min Range: -6.1798
Max Act: 6.0860. Min Act: -0.1700
Data Index: 4504774 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1798. Min Range: -6.1798
Max Act: 6.0548. Min Act: -0.1700
Data Index: 8208754 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1798. Min Range: -6.1798
Max Act: 6.0235. Min Act: -0.1700
Data Index: 3151968 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.9298. Min Act: -0.1700
Data Index: 6962382 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8985. Min Act: -0.1700
Data Index: 2901506 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1221446 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8673. Min Act: -0.1700
Data Index: 496331 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8360. Min Act: -0.1700
Data Index: 4857650 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8360. Min Act: -0.1700
Data Index: 6636555 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8360. Min Act: -0.1700
Data Index: 7543234 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8048. Min Act: -0.1700
Data Index: 4777395 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7687996 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8048. Min Act: -0.1700
Data Index: 15563 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.8048. Min Act: -0.1700
Data Index: 8117533 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2602595 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2767308 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7836226 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.7423. Min Act: -0.1700
Data Index: 3686851 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1798. Min Range: -6.1798
Max Act: 5.7423. Min Act: -0.1700
Data Index: 444303 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19