Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.5417. Min Act: -0.1700
Data Index: 8745476 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.4480. Min Act: -0.1700
Data Index: 8825768 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.4480. Min Act: -0.1700
Data Index: 3383442 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.3542. Min Act: -0.1700
Data Index: 8612703 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1980. Min Act: -0.1700
Data Index: 5626231 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1980. Min Act: -0.1700
Data Index: 4586740 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1667. Min Act: -0.1700
Data Index: 3010787 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1355. Min Act: -0.1700
Data Index: 6245117 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1355. Min Act: -0.1700
Data Index: 3096255 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1042. Min Act: -0.1700
Data Index: 7455009 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.1042. Min Act: -0.1700
Data Index: 6011239 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0729. Min Act: -0.1700
Data Index: 204870 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0729. Min Act: -0.1700
Data Index: 7515563 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4096947 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0104. Min Act: -0.1700
Data Index: 8251872 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0104. Min Act: -0.1700
Data Index: 1692684 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5417. Min Range: -4.5417
Max Act: 4.0104. Min Act: -0.1700
Data Index: 1522707 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5417. Min Range: -4.5417
Max Act: 3.9792. Min Act: -0.1700
Data Index: 7043414 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5417. Min Range: -4.5417
Max Act: 3.9792. Min Act: -0.1700
Data Index: 1308001 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5417. Min Range: -4.5417
Max Act: 3.9792. Min Act: -0.1700
Data Index: 5728475 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19