Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.3762. Min Act: -0.1700
Data Index: 8722604 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.3137. Min Act: -0.1700
Data Index: 5114643 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.1262. Min Act: -0.1700
Data Index: 2608071 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.1262. Min Act: -0.1700
Data Index: 2263122 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.0637. Min Act: -0.1700
Data Index: 368873 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.0637. Min Act: -0.1700
Data Index: 517346 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3762. Min Range: -6.3762
Max Act: 6.0012. Min Act: -0.1700
Data Index: 380747 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9700. Min Act: -0.1700
Data Index: 1243663 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9700. Min Act: -0.1700
Data Index: 2716077 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2752088 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9387. Min Act: -0.1700
Data Index: 5810007 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9075. Min Act: -0.1700
Data Index: 1967590 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9075. Min Act: -0.1700
Data Index: 2897383 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8762. Min Act: -0.1700
Data Index: 1472312 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8762. Min Act: -0.1700
Data Index: 397168 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.9075. Min Act: -0.1700
Data Index: 91 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8450. Min Act: -0.1700
Data Index: 2229755 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8450. Min Act: -0.1700
Data Index: 4918859 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8762. Min Act: -0.1700
Data Index: 2665534 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3762. Min Range: -6.3762
Max Act: 5.8450. Min Act: -0.1700
Data Index: 813 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19