Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.8851. Min Act: -0.1700
Data Index: 1831129 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.7288. Min Act: -0.1700
Data Index: 7488037 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6975. Min Act: -0.1700
Data Index: 1746987 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6975. Min Act: -0.1700
Data Index: 6668772 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.7600. Min Act: -0.1700
Data Index: 5193765 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6975. Min Act: -0.1700
Data Index: 8177886 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6662. Min Act: -0.1700
Data Index: 3672291 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6662. Min Act: -0.1700
Data Index: 2952020 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6349. Min Act: -0.1700
Data Index: 4523904 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6662. Min Act: -0.1700
Data Index: 4407384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6349. Min Act: -0.1700
Data Index: 5202172 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6349. Min Act: -0.1700
Data Index: 1233967 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6349. Min Act: -0.1700
Data Index: 8388938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6349. Min Act: -0.1700
Data Index: 7970549 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6036. Min Act: -0.1700
Data Index: 5738173 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6036. Min Act: -0.1700
Data Index: 140422 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.5723. Min Act: -0.1700
Data Index: 6259649 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6036. Min Act: -0.1700
Data Index: 6616016 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6036. Min Act: -0.1700
Data Index: 577549 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8851. Min Range: -3.8851
Max Act: 3.6036. Min Act: -0.1700
Data Index: 3233070 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19