Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.6798. Min Act: -0.1700
Data Index: 3611319 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.6798. Min Act: -0.1700
Data Index: 2047893 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.6173. Min Act: -0.1700
Data Index: 3824647 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.5860. Min Act: -0.1700
Data Index: 8223769 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.4923. Min Act: -0.1700
Data Index: 3724020 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.4923. Min Act: -0.1700
Data Index: 4647304 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3985. Min Act: -0.1700
Data Index: 4382959 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3985. Min Act: -0.1700
Data Index: 6951755 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3985. Min Act: -0.1700
Data Index: 3033991 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3048. Min Act: -0.1700
Data Index: 2544995 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3048. Min Act: -0.1700
Data Index: 8723122 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.3048. Min Act: -0.1700
Data Index: 4174434 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.2735. Min Act: -0.1700
Data Index: 2945266 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.1798. Min Act: -0.1700
Data Index: 7769126 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.1485. Min Act: -0.1700
Data Index: 302733 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.0860. Min Act: -0.1700
Data Index: 7497639 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.0860. Min Act: -0.1700
Data Index: 1792813 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.0548. Min Act: -0.1700
Data Index: 7160639 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.0860. Min Act: -0.1700
Data Index: 7367188 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6798. Min Range: -7.6798
Max Act: 7.0548. Min Act: -0.1700
Data Index: 7569806 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19