Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5980 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.1777. Min Act: -0.1700
Data Index: 4419042 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0840. Min Act: -0.1700
Data Index: 5830410 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9902. Min Act: -0.1700
Data Index: 8190309 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 1560448 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8651. Min Act: -0.1700
Data Index: 2725867 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8026. Min Act: -0.1700
Data Index: 5382598 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8339. Min Act: -0.1700
Data Index: 2763995 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8339. Min Act: -0.1700
Data Index: 3360603 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8339. Min Act: -0.1700
Data Index: 3469126 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8651. Min Act: -0.1700
Data Index: 1161299 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 7181742 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8026. Min Act: -0.1700
Data Index: 6834292 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8026. Min Act: -0.1700
Data Index: 550416 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8026. Min Act: -0.1700
Data Index: 8407355 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 33232 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 2881670 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7400. Min Act: -0.1700
Data Index: 2618763 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 8262454 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 2388389 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.7713. Min Act: -0.1700
Data Index: 5836123 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19