Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5039 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1721. Min Range: -8.1721
Max Act: 8.1721. Min Act: -0.1700
Data Index: 4778086 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1721. Min Range: -8.1721
Max Act: 8.1096. Min Act: -0.1700
Data Index: 931290 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1721. Min Range: -8.1721
Max Act: 8.0471. Min Act: -0.1700
Data Index: 4098886 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.9846. Min Act: -0.1700
Data Index: 8753347 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.8596. Min Act: -0.1700
Data Index: 4513509 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.8596. Min Act: -0.1700
Data Index: 3218419 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.8596. Min Act: -0.1700
Data Index: 8319821 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.7971. Min Act: -0.1700
Data Index: 2055857 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.7346. Min Act: -0.1700
Data Index: 3616210 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.7346. Min Act: -0.1700
Data Index: 2781011 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.7346. Min Act: -0.1700
Data Index: 701186 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.7346. Min Act: -0.1700
Data Index: 2062766 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6721. Min Act: -0.1700
Data Index: 1567822 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6721. Min Act: -0.1700
Data Index: 4625273 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6721. Min Act: -0.1700
Data Index: 3516434 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6721. Min Act: -0.1700
Data Index: 4915306 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6721. Min Act: -0.1700
Data Index: 1380947 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6096. Min Act: -0.1700
Data Index: 1492283 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6096. Min Act: -0.1700
Data Index: 4098899 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1721. Min Range: -8.1721
Max Act: 7.6096. Min Act: -0.1700
Data Index: 2916755 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19