Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.9559. Min Act: -0.1700
Data Index: 1246139 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.6122. Min Act: -0.1700
Data Index: 1879325 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.5497. Min Act: -0.1700
Data Index: 5992681 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.4872. Min Act: -0.1700
Data Index: 1846489 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.4559. Min Act: -0.1700
Data Index: 6870726 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.4559. Min Act: -0.1700
Data Index: 6512404 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.3309. Min Act: -0.1700
Data Index: 7705207 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.3309. Min Act: -0.1700
Data Index: 188260 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.2997. Min Act: -0.1700
Data Index: 3161584 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.2684. Min Act: -0.1700
Data Index: 8001280 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.2372. Min Act: -0.1700
Data Index: 3687526 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.2059. Min Act: -0.1700
Data Index: 1601460 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1434. Min Act: -0.1700
Data Index: 5761301 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1434. Min Act: -0.1700
Data Index: 186302 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1434. Min Act: -0.1700
Data Index: 5901547 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1747. Min Act: -0.1700
Data Index: 2190634 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1434. Min Act: -0.1700
Data Index: 1152173 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1434. Min Act: -0.1700
Data Index: 8177313 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.1122. Min Act: -0.1700
Data Index: 5582390 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9559. Min Range: -6.9559
Max Act: 6.0809. Min Act: -0.1700
Data Index: 6169323 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19