Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6379 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.7684. Min Act: -0.1700
Data Index: 1457413 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.5809. Min Act: -0.1700
Data Index: 1488543 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.3309. Min Act: -0.1700
Data Index: 8587404 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.2997. Min Act: -0.1700
Data Index: 7839202 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.2997. Min Act: -0.1700
Data Index: 3785174 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.2684. Min Act: -0.1700
Data Index: 5389344 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.2059. Min Act: -0.1700
Data Index: 7607349 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.1434. Min Act: -0.1700
Data Index: 5221088 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.1434. Min Act: -0.1700
Data Index: 5548746 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.0809. Min Act: -0.1700
Data Index: 3098560 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.0809. Min Act: -0.1700
Data Index: 2200895 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.0497. Min Act: -0.1700
Data Index: 3935501 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7684. Min Range: -7.7684
Max Act: 7.0184. Min Act: -0.1700
Data Index: 7359490 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.9872. Min Act: -0.1700
Data Index: 7970430 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.9872. Min Act: -0.1700
Data Index: 1865555 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.9559. Min Act: -0.1700
Data Index: 3782755 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.8934. Min Act: -0.1700
Data Index: 3165530 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.8934. Min Act: -0.1700
Data Index: 6931778 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.7997. Min Act: -0.1700
Data Index: 3403833 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7684. Min Range: -7.7684
Max Act: 6.8309. Min Act: -0.1700
Data Index: 1297385 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19