Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.6245. Min Act: -0.1700
Data Index: 6221791 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.3432. Min Act: -0.1700
Data Index: 5018746 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.3120. Min Act: -0.1700
Data Index: 5311738 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.3432. Min Act: -0.1700
Data Index: 6908430 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 984079 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 853142 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 2155146 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3868667 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 2343545 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6948624 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3640517 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.2495. Min Act: -0.1700
Data Index: 126026 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1870. Min Act: -0.1700
Data Index: 8006726 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1870. Min Act: -0.1700
Data Index: 2286409 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1870. Min Act: -0.1700
Data Index: 6534550 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1870. Min Act: -0.1700
Data Index: 225197 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1870. Min Act: -0.1700
Data Index: 962207 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1557. Min Act: -0.1700
Data Index: 381554 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1557. Min Act: -0.1700
Data Index: 3984998 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6245. Min Range: -6.6245
Max Act: 6.1557. Min Act: -0.1700
Data Index: 507009 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19