Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3920 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.9851. Min Act: -0.1700
Data Index: 720405 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.7664. Min Act: -0.1700
Data Index: 6663978 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.6414. Min Act: -0.1700
Data Index: 1110830 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3550064 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.6101. Min Act: -0.1700
Data Index: 161207 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.6101. Min Act: -0.1700
Data Index: 4932122 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.6101. Min Act: -0.1700
Data Index: 5259126 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.5476. Min Act: -0.1700
Data Index: 7946609 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.4851. Min Act: -0.1700
Data Index: 6376373 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.4851. Min Act: -0.1700
Data Index: 3006034 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.4226. Min Act: -0.1700
Data Index: 5906177 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.4226. Min Act: -0.1700
Data Index: 1826536 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.4226. Min Act: -0.1700
Data Index: 4588582 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3914. Min Act: -0.1700
Data Index: 3072244 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3914. Min Act: -0.1700
Data Index: 3291109 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3601. Min Act: -0.1700
Data Index: 1636158 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3289. Min Act: -0.1700
Data Index: 5090509 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3601. Min Act: -0.1700
Data Index: 8763692 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3289. Min Act: -0.1700
Data Index: 1139479 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9851. Min Range: -5.9851
Max Act: 5.3289. Min Act: -0.1700
Data Index: 231418 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19