Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.9923. Min Act: -0.1700
Data Index: 1535153 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.8048. Min Act: -0.1700
Data Index: 5262474 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.8048. Min Act: -0.1700
Data Index: 5721287 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.8048. Min Act: -0.1700
Data Index: 2193932 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.6798. Min Act: -0.1700
Data Index: 4472452 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.3673. Min Act: -0.1700
Data Index: 6102397 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.3048. Min Act: -0.1700
Data Index: 5679084 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.3048. Min Act: -0.1700
Data Index: 6670045 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.2423. Min Act: -0.1700
Data Index: 3949141 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1798. Min Act: -0.1700
Data Index: 2451878 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1798. Min Act: -0.1700
Data Index: 6077042 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1798. Min Act: -0.1700
Data Index: 7649681 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1798. Min Act: -0.1700
Data Index: 703692 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1173. Min Act: -0.1700
Data Index: 444901 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1173. Min Act: -0.1700
Data Index: 2969911 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.1173. Min Act: -0.1700
Data Index: 4844656 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.0548. Min Act: -0.1700
Data Index: 5662222 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9923. Min Range: -12.9923
Max Act: 12.0548. Min Act: -0.1700
Data Index: 8649727 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9923. Min Range: -12.9923
Max Act: 11.9923. Min Act: -0.1699
Data Index: 6610395 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9923. Min Range: -12.9923
Max Act: 11.9923. Min Act: -0.1700
Data Index: 4486319 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19