Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6040. Min Range: -6.6040
Max Act: 6.6040. Min Act: -0.1700
Data Index: 6125995 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.9790. Min Act: -0.1700
Data Index: 1850674 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.8540. Min Act: -0.1700
Data Index: 4078113 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.8540. Min Act: -0.1700
Data Index: 5290645 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4177853 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.7290. Min Act: -0.1700
Data Index: 8545398 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.7290. Min Act: -0.1700
Data Index: 7537869 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5477259 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6977. Min Act: -0.1700
Data Index: 7876564 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6977. Min Act: -0.1700
Data Index: 576656 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5290642 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6665. Min Act: -0.1700
Data Index: 5152358 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6665. Min Act: -0.1700
Data Index: 8591821 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5062874 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5520090 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.6040. Min Act: -0.1700
Data Index: 3397679 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4895031 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.5415. Min Act: -0.1700
Data Index: 7307215 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.5102. Min Act: -0.1700
Data Index: 8144741 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6040. Min Range: -6.6040
Max Act: 5.4477. Min Act: -0.1700
Data Index: 1352916 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19