Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6602. Min Range: -7.6602
Max Act: 7.6602. Min Act: -0.1700
Data Index: 7794527 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6602. Min Range: -7.6602
Max Act: 7.5977. Min Act: -0.1700
Data Index: 6254349 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6602. Min Range: -7.6602
Max Act: 7.2539. Min Act: -0.1700
Data Index: 2516488 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6602. Min Range: -7.6602
Max Act: 7.2227. Min Act: -0.1700
Data Index: 4452855 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6602. Min Range: -7.6602
Max Act: 7.0664. Min Act: -0.1700
Data Index: 1287778 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.9414. Min Act: -0.1700
Data Index: 680520 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.9414. Min Act: -0.1700
Data Index: 7761511 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.9102. Min Act: -0.1700
Data Index: 633401 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.9102. Min Act: -0.1700
Data Index: 1547690 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.8477. Min Act: -0.1700
Data Index: 1944455 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7814629 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.8164. Min Act: -0.1700
Data Index: 1755164 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.8164. Min Act: -0.1700
Data Index: 4451525 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.8477. Min Act: -0.1700
Data Index: 4889960 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.7539. Min Act: -0.1700
Data Index: 5397576 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.7227. Min Act: -0.1700
Data Index: 6939291 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.7227. Min Act: -0.1700
Data Index: 6941861 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4355983 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.6914. Min Act: -0.1700
Data Index: 6831235 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6602. Min Range: -7.6602
Max Act: 6.6914. Min Act: -0.1700
Data Index: 869419 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19