Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.3139. Min Act: -0.1700
Data Index: 5618416 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.2826. Min Act: -0.1700
Data Index: 2722657 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.2201. Min Act: -0.1700
Data Index: 642047 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.2201. Min Act: -0.1700
Data Index: 6535296 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.2201. Min Act: -0.1700
Data Index: 5372564 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.1889. Min Act: -0.1700
Data Index: 3063331 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.1576. Min Act: -0.1700
Data Index: 5610385 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0951. Min Act: -0.1700
Data Index: 6176215 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.1264. Min Act: -0.1700
Data Index: 1225301 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0951. Min Act: -0.1700
Data Index: 4993595 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0951. Min Act: -0.1700
Data Index: 4268079 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0326. Min Act: -0.1700
Data Index: 6302224 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0326. Min Act: -0.1700
Data Index: 2016875 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0326. Min Act: -0.1700
Data Index: 4680676 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0326. Min Act: -0.1700
Data Index: 3706442 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0014. Min Act: -0.1700
Data Index: 2620660 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0014. Min Act: -0.1700
Data Index: 1054368 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0014. Min Act: -0.1700
Data Index: 7635329 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3139. Min Range: -5.3139
Max Act: 5.0014. Min Act: -0.1700
Data Index: 4369039 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3139. Min Range: -5.3139
Max Act: 4.9701. Min Act: -0.1700
Data Index: 5609024 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19