Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1610. Min Range: -8.1610
Max Act: 8.1610. Min Act: -0.1700
Data Index: 2182979 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1610. Min Range: -8.1610
Max Act: 8.0985. Min Act: -0.1700
Data Index: 5344415 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.9735. Min Act: -0.1700
Data Index: 4703004 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7860. Min Act: -0.1700
Data Index: 8408696 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7548. Min Act: -0.1700
Data Index: 6437783 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7548. Min Act: -0.1700
Data Index: 639935 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7235. Min Act: -0.1700
Data Index: 7276898 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7235. Min Act: -0.1700
Data Index: 8557416 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.7235. Min Act: -0.1700
Data Index: 1720874 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6923. Min Act: -0.1700
Data Index: 798682 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6923. Min Act: -0.1700
Data Index: 6574135 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6610. Min Act: -0.1700
Data Index: 3853071 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6298. Min Act: -0.1700
Data Index: 6599870 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6298. Min Act: -0.1700
Data Index: 2580168 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.6298. Min Act: -0.1700
Data Index: 6331804 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.5673. Min Act: -0.1700
Data Index: 8213188 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.5673. Min Act: -0.1700
Data Index: 1930583 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.5673. Min Act: -0.1700
Data Index: 2242653 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.5360. Min Act: -0.1700
Data Index: 3794919 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1610. Min Range: -8.1610
Max Act: 7.5985. Min Act: -0.1700
Data Index: 67129 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19