Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.2465. Min Act: -0.1700
Data Index: 3094839 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 3094852 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1606639 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1527. Min Act: -0.1700
Data Index: 1606652 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3094830 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 7165417 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3094843 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0590. Min Act: -0.1700
Data Index: 7165408 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0590. Min Act: -0.1700
Data Index: 7165407 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0590. Min Act: -0.1700
Data Index: 5443591 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0277. Min Act: -0.1700
Data Index: 8128928 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0277. Min Act: -0.1700
Data Index: 5443603 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9965. Min Act: -0.1700
Data Index: 8128941 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3560457 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 4926809 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 1867573 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 3094831 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.8715. Min Act: -0.1700
Data Index: 1867585 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.8402. Min Act: -0.1700
Data Index: 2830915 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.8402. Min Act: -0.1700
Data Index: 1357003 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19