Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4645 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.7828. Min Act: -0.1700
Data Index: 6778222 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.7203. Min Act: -0.1700
Data Index: 8228455 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7001828 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.7203. Min Act: -0.1700
Data Index: 688074 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.7515. Min Act: -0.1700
Data Index: 1801243 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.6890. Min Act: -0.1700
Data Index: 5819792 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.6265. Min Act: -0.1700
Data Index: 379673 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.5015. Min Act: -0.1700
Data Index: 3899270 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4390. Min Act: -0.1700
Data Index: 1331120 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4390. Min Act: -0.1700
Data Index: 5159128 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4390. Min Act: -0.1700
Data Index: 2493484 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4390. Min Act: -0.1700
Data Index: 2618422 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4078. Min Act: -0.1700
Data Index: 3543673 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.4078. Min Act: -0.1700
Data Index: 6923985 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3765. Min Act: -0.1700
Data Index: 4329831 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3765. Min Act: -0.1700
Data Index: 69492 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3453. Min Act: -0.1700
Data Index: 4787700 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3140. Min Act: -0.1700
Data Index: 5578787 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3765. Min Act: -0.1700
Data Index: 1715493 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7828. Min Range: -6.7828
Max Act: 6.3453. Min Act: -0.1700
Data Index: 5080337 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19