Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.5284. Min Act: -0.1700
Data Index: 4284152 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.4034. Min Act: -0.1700
Data Index: 4728675 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.2159. Min Act: -0.1700
Data Index: 840896 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.2159. Min Act: -0.1700
Data Index: 897321 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.0909. Min Act: -0.1700
Data Index: 8734885 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5284. Min Range: -8.5284
Max Act: 8.0909. Min Act: -0.1700
Data Index: 7033925 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.9659. Min Act: -0.1700
Data Index: 1036908 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.9034. Min Act: -0.1700
Data Index: 4755785 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.8409. Min Act: -0.1700
Data Index: 5074435 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.7784. Min Act: -0.1700
Data Index: 3296916 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.7159. Min Act: -0.1700
Data Index: 2740561 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.7159. Min Act: -0.1700
Data Index: 1510876 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.6534. Min Act: -0.1700
Data Index: 7258201 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.6534. Min Act: -0.1700
Data Index: 6252283 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.6534. Min Act: -0.1700
Data Index: 2687265 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.6534. Min Act: -0.1700
Data Index: 3952067 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.6534. Min Act: -0.1700
Data Index: 4633540 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.5284. Min Act: -0.1700
Data Index: 3957773 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.5909. Min Act: -0.1700
Data Index: 6368080 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5284. Min Range: -8.5284
Max Act: 7.5909. Min Act: -0.1700
Data Index: 162348 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19