Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1438. Min Range: -6.1438
Max Act: 6.1438. Min Act: -0.1700
Data Index: 2126346 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8938. Min Act: -0.1700
Data Index: 8639869 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4541716 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8313. Min Act: -0.1700
Data Index: 30564 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8001. Min Act: -0.1700
Data Index: 70971 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8001. Min Act: -0.1700
Data Index: 4619189 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8001. Min Act: -0.1700
Data Index: 7403458 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7376. Min Act: -0.1700
Data Index: 3745550 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7376. Min Act: -0.1700
Data Index: 539407 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6438. Min Act: -0.1700
Data Index: 1322589 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6438. Min Act: -0.1700
Data Index: 6471769 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6438. Min Act: -0.1700
Data Index: 7932584 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5813. Min Act: -0.1700
Data Index: 4506104 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6126. Min Act: -0.1700
Data Index: 360146 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5501. Min Act: -0.1700
Data Index: 455714 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4194926 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5188. Min Act: -0.1700
Data Index: 4619190 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5188. Min Act: -0.1700
Data Index: 3210037 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5188. Min Act: -0.1700
Data Index: 7001190 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.4876. Min Act: -0.1700
Data Index: 3689174 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19