Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 720 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.8800. Min Act: -0.1700
Data Index: 4886555 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.6925. Min Act: -0.1700
Data Index: 5271469 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6639477 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.6925. Min Act: -0.1700
Data Index: 285481 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.7238. Min Act: -0.1700
Data Index: 6629111 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.6925. Min Act: -0.1700
Data Index: 7196693 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.6300. Min Act: -0.1700
Data Index: 918798 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5988. Min Act: -0.1700
Data Index: 1111542 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5988. Min Act: -0.1700
Data Index: 5871871 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5675. Min Act: -0.1700
Data Index: 413551 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2630063 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6026550 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2513732 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5050. Min Act: -0.1700
Data Index: 1180320 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5050. Min Act: -0.1700
Data Index: 7555653 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.5050. Min Act: -0.1700
Data Index: 1454510 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.4738. Min Act: -0.1700
Data Index: 4875858 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.4738. Min Act: -0.1700
Data Index: 8260117 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.4738. Min Act: -0.1700
Data Index: 5741111 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8800. Min Range: -6.8800
Max Act: 6.4738. Min Act: -0.1700
Data Index: 3830922 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19