Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.4848. Min Act: -0.1700
Data Index: 2538756 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.4535. Min Act: -0.1700
Data Index: 5229119 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.3598. Min Act: -0.1700
Data Index: 795510 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.2660. Min Act: -0.1700
Data Index: 3412771 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.2348. Min Act: -0.1700
Data Index: 7410162 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.2035. Min Act: -0.1700
Data Index: 5882803 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.2035. Min Act: -0.1700
Data Index: 2468794 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1410. Min Act: -0.1700
Data Index: 8358177 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1410. Min Act: -0.1700
Data Index: 969859 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1410. Min Act: -0.1700
Data Index: 7700968 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1410. Min Act: -0.1700
Data Index: 1971505 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0785. Min Act: -0.1700
Data Index: 8577946 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1098. Min Act: -0.1700
Data Index: 4396427 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1098. Min Act: -0.1700
Data Index: 5171302 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.1098. Min Act: -0.1700
Data Index: 6687083 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0785. Min Act: -0.1700
Data Index: 887655 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0785. Min Act: -0.1700
Data Index: 8573538 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0785. Min Act: -0.1700
Data Index: 2464630 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0785. Min Act: -0.1700
Data Index: 7677559 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4848. Min Range: -7.4848
Max Act: 7.0473. Min Act: -0.1700
Data Index: 6371469 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19