Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.4438. Min Act: -0.1700
Data Index: 8399548 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.2250. Min Act: -0.1700
Data Index: 419011 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.2250. Min Act: -0.1700
Data Index: 2183641 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1938. Min Act: -0.1700
Data Index: 2256174 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1313. Min Act: -0.1700
Data Index: 729270 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1313. Min Act: -0.1700
Data Index: 2736143 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1625. Min Act: -0.1700
Data Index: 5230679 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1313. Min Act: -0.1700
Data Index: 6422717 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0688. Min Act: -0.1700
Data Index: 4614723 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.1000. Min Act: -0.1700
Data Index: 8055727 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0375. Min Act: -0.1700
Data Index: 7400050 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5669852 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0063. Min Act: -0.1700
Data Index: 5554730 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5883086 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0375. Min Act: -0.1700
Data Index: 3940765 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0063. Min Act: -0.1700
Data Index: 1566064 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4438. Min Range: -5.4438
Max Act: 5.0063. Min Act: -0.1700
Data Index: 2569240 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4438. Min Range: -5.4438
Max Act: 4.9750. Min Act: -0.1700
Data Index: 4339958 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4438. Min Range: -5.4438
Max Act: 4.9750. Min Act: -0.1700
Data Index: 5591087 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4438. Min Range: -5.4438
Max Act: 4.9750. Min Act: -0.1700
Data Index: 1040853 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19