Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.8646. Min Act: -0.1700
Data Index: 1134416 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.8646. Min Act: -0.1700
Data Index: 2435131 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.8020. Min Act: -0.1700
Data Index: 884916 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7395. Min Act: -0.1700
Data Index: 6172186 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7708. Min Act: -0.1700
Data Index: 5997769 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7708. Min Act: -0.1700
Data Index: 360244 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7238. Min Act: -0.1700
Data Index: 8378934 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7395. Min Act: -0.1700
Data Index: 4629955 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7395. Min Act: -0.1700
Data Index: 396728 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6925. Min Act: -0.1700
Data Index: 5486642 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7082. Min Act: -0.1700
Data Index: 458704 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6456. Min Act: -0.1700
Data Index: 4376915 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6456. Min Act: -0.1700
Data Index: 7233961 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6300. Min Act: -0.1700
Data Index: 7704101 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6300. Min Act: -0.1700
Data Index: 1810400 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5830. Min Act: -0.1700
Data Index: 3549912 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5674. Min Act: -0.1700
Data Index: 7009545 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8147256 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5987. Min Act: -0.1700
Data Index: 154941 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5987. Min Act: -0.1700
Data Index: 5132059 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19