Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4039 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.7394. Min Act: -0.1700
Data Index: 1833265 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.6144. Min Act: -0.1700
Data Index: 2717385 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.5519. Min Act: -0.1700
Data Index: 4572215 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.5519. Min Act: -0.1700
Data Index: 4266729 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.5519. Min Act: -0.1700
Data Index: 4452511 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.4269. Min Act: -0.1700
Data Index: 4742994 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.4269. Min Act: -0.1700
Data Index: 1939567 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.3644. Min Act: -0.1700
Data Index: 5471736 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.3019. Min Act: -0.1700
Data Index: 4335054 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1769. Min Act: -0.1700
Data Index: 5491416 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.2394. Min Act: -0.1700
Data Index: 308948 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1769. Min Act: -0.1700
Data Index: 566744 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1144. Min Act: -0.1700
Data Index: 1975220 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1144. Min Act: -0.1700
Data Index: 7447760 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1144. Min Act: -0.1700
Data Index: 5475188 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1144. Min Act: -0.1700
Data Index: 8554922 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1769. Min Act: -0.1700
Data Index: 1333585 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.1144. Min Act: -0.1700
Data Index: 7456202 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.0519. Min Act: -0.1700
Data Index: 4006124 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.7394. Min Range: -13.7394
Max Act: 13.0519. Min Act: -0.1700
Data Index: 3805430 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19