Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 3727914 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 6832878 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3815. Min Act: -0.1700
Data Index: 5703452 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2565. Min Act: -0.1700
Data Index: 7118686 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2565. Min Act: -0.1700
Data Index: 5955029 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1315. Min Act: -0.1700
Data Index: 1475146 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9753. Min Act: -0.1700
Data Index: 5426850 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.0065. Min Act: -0.1700
Data Index: 7881368 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9753. Min Act: -0.1700
Data Index: 1326956 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9753. Min Act: -0.1700
Data Index: 5326754 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9440. Min Act: -0.1700
Data Index: 8355349 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9128. Min Act: -0.1700
Data Index: 7004082 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9440. Min Act: -0.1700
Data Index: 519011 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9440. Min Act: -0.1700
Data Index: 3577085 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9128. Min Act: -0.1700
Data Index: 4438182 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9128. Min Act: -0.1700
Data Index: 4726246 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8815. Min Act: -0.1700
Data Index: 1472716 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8815. Min Act: -0.1700
Data Index: 84227 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8815. Min Act: -0.1700
Data Index: 865943 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8815. Min Act: -0.1700
Data Index: 6832122 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19