Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.8641. Min Act: -0.1700
Data Index: 1744048 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.7391. Min Act: -0.1700
Data Index: 878578 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.5829. Min Act: -0.1700
Data Index: 1273108 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.5204. Min Act: -0.1700
Data Index: 1323960 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.4891. Min Act: -0.1700
Data Index: 5362751 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.4579. Min Act: -0.1700
Data Index: 3123546 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3954. Min Act: -0.1700
Data Index: 5379376 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.4266. Min Act: -0.1700
Data Index: 7475834 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3954. Min Act: -0.1700
Data Index: 5862356 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3641. Min Act: -0.1700
Data Index: 5620534 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3641. Min Act: -0.1700
Data Index: 6358958 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3954. Min Act: -0.1700
Data Index: 2466658 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3641. Min Act: -0.1700
Data Index: 3556105 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3329. Min Act: -0.1700
Data Index: 3547641 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3329. Min Act: -0.1700
Data Index: 2117364 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1662063 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1558822 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3016. Min Act: -0.1700
Data Index: 4459302 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.3016. Min Act: -0.1700
Data Index: 383046 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8641. Min Range: -5.8641
Max Act: 5.2704. Min Act: -0.1700
Data Index: 6828145 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19