Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.6251. Min Act: -0.1700
Data Index: 2618620 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2813. Min Act: -0.1700
Data Index: 7042489 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 7781875 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 4766515 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1876. Min Act: -0.1700
Data Index: 8331904 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.0938. Min Act: -0.1700
Data Index: 6669227 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.9376. Min Act: -0.1700
Data Index: 4400170 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.9376. Min Act: -0.1700
Data Index: 326362 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.9063. Min Act: -0.1700
Data Index: 5087476 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.9063. Min Act: -0.1700
Data Index: 262863 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8438. Min Act: -0.1700
Data Index: 3923123 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8751. Min Act: -0.1700
Data Index: 1599326 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8438. Min Act: -0.1700
Data Index: 3670194 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8751. Min Act: -0.1700
Data Index: 8331912 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8438. Min Act: -0.1700
Data Index: 804719 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8438. Min Act: -0.1700
Data Index: 8148876 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.8126. Min Act: -0.1700
Data Index: 5405846 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.7813. Min Act: -0.1700
Data Index: 1687190 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.7813. Min Act: -0.1700
Data Index: 5305776 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6251. Min Range: -5.6251
Max Act: 4.7813. Min Act: -0.1700
Data Index: 8148874 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19