Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3387. Min Act: -0.1700
Data Index: 7271398 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3387. Min Act: -0.1700
Data Index: 1343707 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3387. Min Act: -0.1700
Data Index: 1343706 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3387. Min Act: -0.1700
Data Index: 7271389 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1343727 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1343726 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1054887 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1290154 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 7386984 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 8538313 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 6485651 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 8713471 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 3674324 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2449. Min Act: -0.1700
Data Index: 4458862 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2136. Min Act: -0.1700
Data Index: 5720584 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2449. Min Act: -0.1700
Data Index: 4246669 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2136. Min Act: -0.1700
Data Index: 2470011 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2449. Min Act: -0.1700
Data Index: 5535320 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2762. Min Act: -0.1700
Data Index: 782513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3387. Min Range: -4.3387
Max Act: 4.2449. Min Act: -0.1700
Data Index: 3539465 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19