Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.6605. Min Act: -0.1700
Data Index: 5427915 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.4730. Min Act: -0.1700
Data Index: 4454254 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1394347 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.1917. Min Act: -0.1700
Data Index: 4674887 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.1917. Min Act: -0.1700
Data Index: 3443311 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.1292. Min Act: -0.1700
Data Index: 4569435 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.0355. Min Act: -0.1700
Data Index: 3686721 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6605. Min Range: -6.6605
Max Act: 6.0042. Min Act: -0.1700
Data Index: 3986436 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.9417. Min Act: -0.1700
Data Index: 4488372 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.9417. Min Act: -0.1700
Data Index: 103808 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.9417. Min Act: -0.1700
Data Index: 5886338 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.9105. Min Act: -0.1700
Data Index: 5293955 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.9105. Min Act: -0.1700
Data Index: 6748820 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8792. Min Act: -0.1700
Data Index: 3644296 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8480. Min Act: -0.1700
Data Index: 779821 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8480. Min Act: -0.1700
Data Index: 4438307 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3419191 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 5520305 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 5338055 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6605. Min Range: -6.6605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 6719717 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19