Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1829 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8737. Min Act: -0.1700
Data Index: 7618997 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8737. Min Act: -0.1700
Data Index: 8801077 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8578. Min Act: -0.1700
Data Index: 3554979 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8419. Min Act: -0.1700
Data Index: 1611655 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 2079413 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8260. Min Act: -0.1700
Data Index: 3389075 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8260. Min Act: -0.1700
Data Index: 8486826 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 6564508 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7942. Min Act: -0.1700
Data Index: 6827748 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7623. Min Act: -0.1700
Data Index: 8240774 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 543951 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7623. Min Act: -0.1700
Data Index: 805509 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 5490941 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7623. Min Act: -0.1700
Data Index: 3583138 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7623. Min Act: -0.1700
Data Index: 6555540 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7304. Min Act: -0.1700
Data Index: 6194541 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7304. Min Act: -0.1700
Data Index: 5358227 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7304. Min Act: -0.1700
Data Index: 4503754 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7304. Min Act: -0.1700
Data Index: 2029446 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7144. Min Act: -0.1700
Data Index: 266899 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19