Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5061. Min Range: -9.5061
Max Act: 9.5061. Min Act: -0.1700
Data Index: 1198480 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5061. Min Range: -9.5061
Max Act: 9.1311. Min Act: -0.1700
Data Index: 637892 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5061. Min Range: -9.5061
Max Act: 9.0686. Min Act: -0.1700
Data Index: 4758095 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5061. Min Range: -9.5061
Max Act: 9.0686. Min Act: -0.1700
Data Index: 637896 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.9436. Min Act: -0.1700
Data Index: 1626144 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.9436. Min Act: -0.1700
Data Index: 8816228 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.8811. Min Act: -0.1700
Data Index: 1344969 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.6311. Min Act: -0.1700
Data Index: 7939320 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.6311. Min Act: -0.1700
Data Index: 7972601 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.6311. Min Act: -0.1700
Data Index: 6317615 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.5686. Min Act: -0.1700
Data Index: 8094740 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.6936. Min Act: -0.1700
Data Index: 5821354 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.5686. Min Act: -0.1700
Data Index: 2355921 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.5061. Min Act: -0.1700
Data Index: 4385705 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.5061. Min Act: -0.1700
Data Index: 2074753 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.4436. Min Act: -0.1700
Data Index: 5678099 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.4436. Min Act: -0.1700
Data Index: 5806498 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.4436. Min Act: -0.1700
Data Index: 8347208 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.4436. Min Act: -0.1700
Data Index: 871722 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5061. Min Range: -9.5061
Max Act: 8.3811. Min Act: -0.1700
Data Index: 299802 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19