Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6504. Min Act: -0.1700
Data Index: 6404989 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4629. Min Act: -0.1700
Data Index: 3324358 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4316. Min Act: -0.1700
Data Index: 943717 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.3379. Min Act: -0.1700
Data Index: 62290 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7642974 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2754. Min Act: -0.1700
Data Index: 8542806 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2754. Min Act: -0.1700
Data Index: 297923 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1816. Min Act: -0.1700
Data Index: 4546007 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1816. Min Act: -0.1700
Data Index: 121868 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 38940 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 7970508 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 1325864 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 5845183 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 2069562 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7960336 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1191. Min Act: -0.1700
Data Index: 5612105 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7136408 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7921679 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.0879. Min Act: -0.1700
Data Index: 1786162 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.0879. Min Act: -0.1700
Data Index: 4231601 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19