Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.8681. Min Act: -0.1700
Data Index: 7390916 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.8368. Min Act: -0.1700
Data Index: 2150806 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.8368. Min Act: -0.1700
Data Index: 1708898 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7743. Min Act: -0.1700
Data Index: 4188248 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7430. Min Act: -0.1700
Data Index: 5677613 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7430. Min Act: -0.1700
Data Index: 6409294 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7430. Min Act: -0.1700
Data Index: 6409285 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6409290 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.6804. Min Act: -0.1700
Data Index: 6409280 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 4188249 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6349107 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6349102 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 953374 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6349093 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 4188244 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 3364982 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 2487036 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 5677614 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 2150810 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7117. Min Act: -0.1700
Data Index: 5677599 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19