Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.9841. Min Act: -0.1700
Data Index: 6163795 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.5466. Min Act: -0.1700
Data Index: 7236857 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.4216. Min Act: -0.1700
Data Index: 179215 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.2966. Min Act: -0.1700
Data Index: 2171372 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.3591. Min Act: -0.1700
Data Index: 8256921 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.2341. Min Act: -0.1700
Data Index: 8128275 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1716. Min Act: -0.1700
Data Index: 6861532 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.2341. Min Act: -0.1700
Data Index: 3378792 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1716. Min Act: -0.1700
Data Index: 8736466 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.2341. Min Act: -0.1700
Data Index: 2194028 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1716. Min Act: -0.1700
Data Index: 5221879 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1091. Min Act: -0.1700
Data Index: 5095551 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.2341. Min Act: -0.1700
Data Index: 2310985 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1716. Min Act: -0.1700
Data Index: 5071098 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1091. Min Act: -0.1700
Data Index: 2170551 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1091. Min Act: -0.1700
Data Index: 3754786 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1716. Min Act: -0.1700
Data Index: 1675106 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.1091. Min Act: -0.1700
Data Index: 5181197 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9841. Min Range: -8.9841
Max Act: 8.0466. Min Act: -0.1700
Data Index: 7915220 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9841. Min Range: -8.9841
Max Act: 7.9841. Min Act: -0.1700
Data Index: 7844887 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19