Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.8063. Min Act: -0.1700
Data Index: 4103036 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.6501. Min Act: -0.1700
Data Index: 6664613 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.6501. Min Act: -0.1700
Data Index: 3010139 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.5563. Min Act: -0.1700
Data Index: 3507856 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.5251. Min Act: -0.1700
Data Index: 7337695 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.5251. Min Act: -0.1700
Data Index: 6742281 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4938. Min Act: -0.1700
Data Index: 4132216 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4938. Min Act: -0.1700
Data Index: 2519429 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4938. Min Act: -0.1700
Data Index: 8780104 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4938. Min Act: -0.1700
Data Index: 3529367 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4626. Min Act: -0.1700
Data Index: 7095116 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4313. Min Act: -0.1700
Data Index: 8690243 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4313. Min Act: -0.1700
Data Index: 7459038 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.4001. Min Act: -0.1700
Data Index: 533713 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3688. Min Act: -0.1700
Data Index: 74586 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3376. Min Act: -0.1700
Data Index: 1666968 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3376. Min Act: -0.1700
Data Index: 1118140 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3376. Min Act: -0.1700
Data Index: 1813243 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3063. Min Act: -0.1700
Data Index: 5201819 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8063. Min Range: -6.8063
Max Act: 6.3063. Min Act: -0.1700
Data Index: 522814 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19