Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.6016. Min Act: -0.1700
Data Index: 3825045 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.4766. Min Act: -0.1700
Data Index: 6936179 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.2891. Min Act: -0.1700
Data Index: 6641355 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.2266. Min Act: -0.1700
Data Index: 6300791 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.1641. Min Act: -0.1700
Data Index: 7277445 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.1329. Min Act: -0.1700
Data Index: 2868039 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.0704. Min Act: -0.1700
Data Index: 1772648 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6016. Min Range: -8.6016
Max Act: 8.0079. Min Act: -0.1700
Data Index: 6351944 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.8516. Min Act: -0.1700
Data Index: 5640112 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.8204. Min Act: -0.1700
Data Index: 5147310 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.7891. Min Act: -0.1700
Data Index: 1034512 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.7579. Min Act: -0.1700
Data Index: 144619 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.7266. Min Act: -0.1700
Data Index: 2536120 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.7266. Min Act: -0.1700
Data Index: 1127748 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6954. Min Act: -0.1700
Data Index: 7991965 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6954. Min Act: -0.1700
Data Index: 6333631 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6641. Min Act: -0.1700
Data Index: 2619767 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6329. Min Act: -0.1700
Data Index: 6812180 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6016. Min Act: -0.1700
Data Index: 1645402 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6016. Min Range: -8.6016
Max Act: 7.6016. Min Act: -0.1700
Data Index: 6638164 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19