Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1798. Min Range: -8.1798
Max Act: 8.1798. Min Act: -0.1700
Data Index: 7523563 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1798. Min Range: -8.1798
Max Act: 8.0860. Min Act: -0.1700
Data Index: 8901 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1798. Min Range: -8.1798
Max Act: 8.0860. Min Act: -0.1700
Data Index: 3660309 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1798. Min Range: -8.1798
Max Act: 8.0235. Min Act: -0.1700
Data Index: 7026902 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.9923. Min Act: -0.1699
Data Index: 7026903 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.9610. Min Act: -0.1700
Data Index: 4314104 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.8673. Min Act: -0.1700
Data Index: 3944537 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.8673. Min Act: -0.1700
Data Index: 1428733 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.8360. Min Act: -0.1700
Data Index: 4957120 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.8048. Min Act: -0.1700
Data Index: 6345643 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.8048. Min Act: -0.1700
Data Index: 8906 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.7735. Min Act: -0.1700
Data Index: 5519921 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.7423. Min Act: -0.1700
Data Index: 6188764 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.7423. Min Act: -0.1700
Data Index: 7442195 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.6798. Min Act: -0.1700
Data Index: 2793070 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.7110. Min Act: -0.1700
Data Index: 5697920 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.7110. Min Act: -0.1700
Data Index: 7292902 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.6485. Min Act: -0.1700
Data Index: 59087 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.6798. Min Act: -0.1700
Data Index: 4887148 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1798. Min Range: -8.1798
Max Act: 7.6485. Min Act: -0.1700
Data Index: 3974544 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19