Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8709. Min Act: -0.1700
Data Index: 2836361 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6842404 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7772. Min Act: -0.1700
Data Index: 1661437 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 5947125 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 7364579 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 4367416 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 2427975 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 4118195 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 7192850 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6522. Min Act: -0.1700
Data Index: 4818460 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6209. Min Act: -0.1700
Data Index: 7091168 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6209. Min Act: -0.1700
Data Index: 205475 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6209. Min Act: -0.1700
Data Index: 8694492 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 3504266 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6209. Min Act: -0.1700
Data Index: 4786021 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 8198695 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6209. Min Act: -0.1700
Data Index: 7070455 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 6843856 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 4680469 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 5186693 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19