Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4000. Min Range: -6.4000
Max Act: 6.4000. Min Act: -0.1700
Data Index: 2956512 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.9625. Min Act: -0.1700
Data Index: 3636176 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.8688. Min Act: -0.1700
Data Index: 6714199 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.8063. Min Act: -0.1700
Data Index: 1621567 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.7750. Min Act: -0.1700
Data Index: 16256 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.7438. Min Act: -0.1700
Data Index: 1271417 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 208234 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6813. Min Act: -0.1700
Data Index: 527065 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6813. Min Act: -0.1700
Data Index: 5587405 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6500. Min Act: -0.1700
Data Index: 67941 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6500. Min Act: -0.1700
Data Index: 7487894 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6188. Min Act: -0.1700
Data Index: 8457503 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6188. Min Act: -0.1700
Data Index: 223763 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6188. Min Act: -0.1700
Data Index: 2552698 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.6188. Min Act: -0.1700
Data Index: 2845041 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.5875. Min Act: -0.1700
Data Index: 4659373 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.5875. Min Act: -0.1700
Data Index: 8206682 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.5563. Min Act: -0.1700
Data Index: 2495305 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.5563. Min Act: -0.1700
Data Index: 247995 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4000. Min Range: -6.4000
Max Act: 5.5563. Min Act: -0.1700
Data Index: 1890106 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19