Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.9688. Min Act: -0.1700
Data Index: 8831330 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.9688. Min Act: -0.1700
Data Index: 5206363 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.9063. Min Act: -0.1700
Data Index: 7463610 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.8438. Min Act: -0.1700
Data Index: 835008 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.8438. Min Act: -0.1700
Data Index: 556702 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5938. Min Act: -0.1700
Data Index: 827271 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.6563. Min Act: -0.1700
Data Index: 728396 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.6563. Min Act: -0.1700
Data Index: 1433478 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5938. Min Act: -0.1700
Data Index: 2755244 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5313. Min Act: -0.1700
Data Index: 2325758 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5313. Min Act: -0.1700
Data Index: 4424636 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5313. Min Act: -0.1700
Data Index: 5316673 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.5313. Min Act: -0.1700
Data Index: 8033524 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.4063. Min Act: -0.1700
Data Index: 3428702 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.2813. Min Act: -0.1700
Data Index: 414699 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.3438. Min Act: -0.1700
Data Index: 242067 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.3438. Min Act: -0.1700
Data Index: 7702913 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.2813. Min Act: -0.1700
Data Index: 6854589 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.2813. Min Act: -0.1700
Data Index: 3529190 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9688. Min Range: -9.9688
Max Act: 9.2813. Min Act: -0.1700
Data Index: 4758616 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19