Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4743 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0058. Min Range: -6.0058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 8097639 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0058. Min Range: -6.0058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 3329858 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.9746. Min Act: -0.1700
Data Index: 6234586 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.9746. Min Act: -0.1700
Data Index: 3530644 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.9433. Min Act: -0.1700
Data Index: 265686 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8496. Min Act: -0.1700
Data Index: 3347314 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8496. Min Act: -0.1700
Data Index: 4404107 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8496. Min Act: -0.1700
Data Index: 4328595 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8496. Min Act: -0.1700
Data Index: 5608400 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8496. Min Act: -0.1700
Data Index: 1838936 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8183. Min Act: -0.1700
Data Index: 1245680 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.8183. Min Act: -0.1700
Data Index: 867803 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7871. Min Act: -0.1700
Data Index: 2024354 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7246. Min Act: -0.1700
Data Index: 1499358 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7558. Min Act: -0.1700
Data Index: 7256910 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7246. Min Act: -0.1700
Data Index: 7267382 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7558. Min Act: -0.1700
Data Index: 161413 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7246. Min Act: -0.1700
Data Index: 6169628 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7246. Min Act: -0.1700
Data Index: 229818 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0058. Min Range: -6.0058
Max Act: 5.7246. Min Act: -0.1700
Data Index: 4569424 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19