Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3250. Min Range: -6.3250
Max Act: 6.3250. Min Act: -0.1700
Data Index: 885623 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3250. Min Range: -6.3250
Max Act: 6.0750. Min Act: -0.1700
Data Index: 3803310 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3250. Min Range: -6.3250
Max Act: 6.0438. Min Act: -0.1700
Data Index: 8549414 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.9188. Min Act: -0.1700
Data Index: 7557302 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.8250. Min Act: -0.1700
Data Index: 6751092 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.8250. Min Act: -0.1700
Data Index: 4536014 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.8250. Min Act: -0.1700
Data Index: 4271625 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2081759 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7313. Min Act: -0.1700
Data Index: 761787 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7000. Min Act: -0.1700
Data Index: 1425813 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7000. Min Act: -0.1700
Data Index: 5386645 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7000. Min Act: -0.1700
Data Index: 8822529 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.7000. Min Act: -0.1700
Data Index: 6960430 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6688. Min Act: -0.1700
Data Index: 2861707 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6688. Min Act: -0.1700
Data Index: 6139578 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7356502 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6375. Min Act: -0.1700
Data Index: 1465731 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6375. Min Act: -0.1700
Data Index: 1597940 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.6063. Min Act: -0.1700
Data Index: 4444729 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3250. Min Range: -6.3250
Max Act: 5.5750. Min Act: -0.1700
Data Index: 2836660 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19