Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2254. Min Range: -8.2254
Max Act: 8.2254. Min Act: -0.1700
Data Index: 3886576 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2254. Min Range: -8.2254
Max Act: 8.2254. Min Act: -0.1700
Data Index: 4409721 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2254. Min Range: -8.2254
Max Act: 8.1004. Min Act: -0.1700
Data Index: 1466142 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.9754. Min Act: -0.1700
Data Index: 864785 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.8504. Min Act: -0.1700
Data Index: 5673971 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.7879. Min Act: -0.1700
Data Index: 8689833 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.7879. Min Act: -0.1700
Data Index: 1987042 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.7254. Min Act: -0.1700
Data Index: 6084227 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.7254. Min Act: -0.1700
Data Index: 3199126 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.7254. Min Act: -0.1700
Data Index: 2480491 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.6629. Min Act: -0.1700
Data Index: 6033045 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.6004. Min Act: -0.1700
Data Index: 1540305 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5379. Min Act: -0.1700
Data Index: 4935074 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5379. Min Act: -0.1700
Data Index: 2990392 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5379. Min Act: -0.1700
Data Index: 6910878 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.4754. Min Act: -0.1700
Data Index: 6616565 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5066. Min Act: -0.1700
Data Index: 5012649 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5066. Min Act: -0.1700
Data Index: 298012 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5066. Min Act: -0.1700
Data Index: 7947435 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2254. Min Range: -8.2254
Max Act: 7.5066. Min Act: -0.1700
Data Index: 6738288 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19