Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.7948. Min Act: -0.1700
Data Index: 1464283 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.6698. Min Act: -0.1700
Data Index: 4899529 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.4823. Min Act: -0.1700
Data Index: 4706523 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.4198. Min Act: -0.1700
Data Index: 5446775 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.2948. Min Act: -0.1700
Data Index: 1340707 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.2323. Min Act: -0.1700
Data Index: 8627565 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.2323. Min Act: -0.1700
Data Index: 5984450 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.1698. Min Act: -0.1700
Data Index: 2628864 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.1698. Min Act: -0.1700
Data Index: 1386195 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.1698. Min Act: -0.1700
Data Index: 1491365 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.1073. Min Act: -0.1700
Data Index: 4305808 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.0448. Min Act: -0.1700
Data Index: 6201869 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.0448. Min Act: -0.1700
Data Index: 5874300 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7948. Min Range: -8.7948
Max Act: 8.1073. Min Act: -0.1700
Data Index: 6864899 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.9823. Min Act: -0.1700
Data Index: 7529682 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.8573. Min Act: -0.1700
Data Index: 6827015 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.9198. Min Act: -0.1700
Data Index: 1234487 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.9198. Min Act: -0.1700
Data Index: 496560 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.7948. Min Act: -0.1700
Data Index: 6090816 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7948. Min Range: -8.7948
Max Act: 7.7323. Min Act: -0.1700
Data Index: 5703615 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19