Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0626. Min Act: -0.1700
Data Index: 326423 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0626. Min Act: -0.1700
Data Index: 4390356 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6734109 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9376. Min Act: -0.1700
Data Index: 2596452 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9689. Min Act: -0.1700
Data Index: 3088776 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8751. Min Act: -0.1700
Data Index: 2194149 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9063. Min Act: -0.1700
Data Index: 6974593 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8751. Min Act: -0.1700
Data Index: 1796444 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 8706149 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 8263030 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8125. Min Act: -0.1700
Data Index: 3999355 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8125. Min Act: -0.1700
Data Index: 5395767 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 3999357 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 6839998 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 530486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 5015616 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8438. Min Act: -0.1700
Data Index: 1223869 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6491251 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8125. Min Act: -0.1700
Data Index: 1223871 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6956662 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19