Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.5078. Min Act: -0.1700
Data Index: 2297676 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.3828. Min Act: -0.1700
Data Index: 3599962 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.1953. Min Act: -0.1700
Data Index: 1030417 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.1328. Min Act: -0.1700
Data Index: 2981821 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.1953. Min Act: -0.1700
Data Index: 1119238 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.1328. Min Act: -0.1700
Data Index: 6338596 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.1328. Min Act: -0.1700
Data Index: 1030444 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0703. Min Act: -0.1700
Data Index: 8706109 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0703. Min Act: -0.1700
Data Index: 1030418 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0703. Min Act: -0.1700
Data Index: 5730676 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0078. Min Act: -0.1700
Data Index: 1030446 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0078. Min Act: -0.1700
Data Index: 7579921 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.9453. Min Act: -0.1700
Data Index: 3875319 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0078. Min Act: -0.1700
Data Index: 4920786 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.9453. Min Act: -0.1700
Data Index: 7480116 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.9453. Min Act: -0.1700
Data Index: 8464843 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5078. Min Range: -9.5078
Max Act: 9.0078. Min Act: -0.1700
Data Index: 7387727 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.9453. Min Act: -0.1700
Data Index: 6414146 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.9453. Min Act: -0.1700
Data Index: 5689801 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5078. Min Range: -9.5078
Max Act: 8.8828. Min Act: -0.1700
Data Index: 2936877 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19