Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1031 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0438. Min Range: -8.0438
Max Act: 8.0438. Min Act: -0.1700
Data Index: 3044801 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.8563. Min Act: -0.1700
Data Index: 77867 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.8563. Min Act: -0.1700
Data Index: 7483960 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.8563. Min Act: -0.1698
Data Index: 70140 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.8563. Min Act: -0.1699
Data Index: 6398517 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.8563. Min Act: -0.1699
Data Index: 4172892 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.7938. Min Act: -0.1698
Data Index: 8531968 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.7938. Min Act: -0.1700
Data Index: 8013124 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 8515944 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 723160 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 6122801 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 7478831 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 6573853 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 6519239 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 8202550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 4451884 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 2162587 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6688. Min Act: -0.1700
Data Index: 3894036 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6063. Min Act: -0.1695
Data Index: 5802185 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0438. Min Range: -8.0438
Max Act: 7.6063. Min Act: -0.1700
Data Index: 4512455 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19