Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 17.3840. Min Range: -17.3840
Max Act: 17.3840. Min Act: -0.1700
Data Index: 2813700 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.3840. Min Range: -17.3840
Max Act: 17.0090. Min Act: -0.1700
Data Index: 4863065 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.8840. Min Act: -0.1700
Data Index: 3562082 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.8840. Min Act: -0.1700
Data Index: 6602917 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.7590. Min Act: -0.1700
Data Index: 1134779 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.7590. Min Act: -0.1700
Data Index: 8431859 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.7590. Min Act: -0.1700
Data Index: 613206 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.7590. Min Act: -0.1700
Data Index: 7128594 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.7590. Min Act: -0.1700
Data Index: 2351933 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.6340. Min Act: -0.1700
Data Index: 1965633 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.6340. Min Act: -0.1700
Data Index: 5561446 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.6340. Min Act: -0.1700
Data Index: 5350184 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.6340. Min Act: -0.1700
Data Index: 439406 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.6340. Min Act: -0.1700
Data Index: 3047389 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.5090. Min Act: -0.1700
Data Index: 3295952 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.5090. Min Act: -0.1700
Data Index: 453006 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.3840. Min Act: -0.1700
Data Index: 6291782 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.5090. Min Act: -0.1700
Data Index: 5868108 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.3840. Min Act: -0.1700
Data Index: 8386938 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.3840. Min Range: -17.3840
Max Act: 16.5090. Min Act: -0.1700
Data Index: 3640513 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19