Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.1734. Min Act: -0.1700
Data Index: 1908470 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.1109. Min Act: -0.1700
Data Index: 2325071 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.1109. Min Act: -0.1700
Data Index: 290524 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1241000 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.0484. Min Act: -0.1700
Data Index: 10317 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1734. Min Range: -5.1734
Max Act: 5.0172. Min Act: -0.1700
Data Index: 852364 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.9859. Min Act: -0.1700
Data Index: 2093515 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8922. Min Act: -0.1700
Data Index: 5491558 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8922. Min Act: -0.1700
Data Index: 8680656 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.9234. Min Act: -0.1700
Data Index: 2923880 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.9234. Min Act: -0.1700
Data Index: 42226 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.9234. Min Act: -0.1700
Data Index: 1878775 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8922. Min Act: -0.1700
Data Index: 2065318 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6915475 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8609. Min Act: -0.1700
Data Index: 5068307 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8609. Min Act: -0.1700
Data Index: 121364 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8609. Min Act: -0.1700
Data Index: 8226283 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8609. Min Act: -0.1700
Data Index: 3618133 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8922. Min Act: -0.1700
Data Index: 1558837 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1734. Min Range: -5.1734
Max Act: 4.8609. Min Act: -0.1700
Data Index: 8004563 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19