Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2127. Min Range: -9.2127
Max Act: 9.2127. Min Act: -0.1700
Data Index: 1989016 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2127. Min Range: -9.2127
Max Act: 9.0252. Min Act: -0.1700
Data Index: 6084149 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.9627. Min Act: -0.1700
Data Index: 3297427 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.8377. Min Act: -0.1700
Data Index: 4529171 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.8377. Min Act: -0.1700
Data Index: 1206867 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.7127. Min Act: -0.1700
Data Index: 1911340 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.7127. Min Act: -0.1700
Data Index: 1641190 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.5877. Min Act: -0.1700
Data Index: 3495927 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.5877. Min Act: -0.1700
Data Index: 5140587 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4627. Min Act: -0.1700
Data Index: 5084935 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.5252. Min Act: -0.1700
Data Index: 864544 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4627. Min Act: -0.1700
Data Index: 5014108 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.5252. Min Act: -0.1700
Data Index: 7126704 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.5877. Min Act: -0.1700
Data Index: 6689954 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4627. Min Act: -0.1700
Data Index: 1451609 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4627. Min Act: -0.1700
Data Index: 6379419 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4002. Min Act: -0.1700
Data Index: 278885 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4002. Min Act: -0.1700
Data Index: 1082561 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4002. Min Act: -0.1700
Data Index: 1873960 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2127. Min Range: -9.2127
Max Act: 8.4002. Min Act: -0.1700
Data Index: 230703 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19