Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7242. Min Act: -0.1700
Data Index: 5326681 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7401. Min Act: -0.1700
Data Index: 6423503 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7242. Min Act: -0.1700
Data Index: 5615146 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7082. Min Act: -0.1700
Data Index: 2703060 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7082. Min Act: -0.1700
Data Index: 6317635 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.7242. Min Act: -0.1700
Data Index: 1333772 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6922. Min Act: -0.1700
Data Index: 5335815 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6922. Min Act: -0.1700
Data Index: 5678090 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6761. Min Act: -0.1700
Data Index: 669497 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6601. Min Act: -0.1700
Data Index: 2264577 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6441. Min Act: -0.1700
Data Index: 3161882 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6601. Min Act: -0.1700
Data Index: 6585617 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6601. Min Act: -0.1700
Data Index: 7731884 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6441. Min Act: -0.1700
Data Index: 6975986 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6441. Min Act: -0.1700
Data Index: 7496982 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6441. Min Act: -0.1700
Data Index: 2004311 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6280. Min Act: -0.1700
Data Index: 5440536 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6601. Min Act: -0.1700
Data Index: 635577 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6119. Min Act: -0.1700
Data Index: 8539912 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7401. Min Range: -2.7401
Max Act: 2.6280. Min Act: -0.1700
Data Index: 3715834 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19