Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9806. Min Act: -0.1700
Data Index: 2204265 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9648. Min Act: -0.1700
Data Index: 6927457 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9173. Min Act: -0.1700
Data Index: 4527769 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9331. Min Act: -0.1700
Data Index: 6419358 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9014. Min Act: -0.1700
Data Index: 4955084 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.9014. Min Act: -0.1700
Data Index: 202034 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8856. Min Act: -0.1700
Data Index: 1104298 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8697. Min Act: -0.1700
Data Index: 3813785 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8697. Min Act: -0.1700
Data Index: 2500284 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8697. Min Act: -0.1700
Data Index: 4128948 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8697. Min Act: -0.1700
Data Index: 6616348 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8538. Min Act: -0.1700
Data Index: 6616352 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8379. Min Act: -0.1700
Data Index: 2953975 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8538. Min Act: -0.1700
Data Index: 8659982 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8538. Min Act: -0.1700
Data Index: 2229172 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8220. Min Act: -0.1700
Data Index: 7697388 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8538. Min Act: -0.1700
Data Index: 734775 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8220. Min Act: -0.1700
Data Index: 589818 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8220. Min Act: -0.1700
Data Index: 5443875 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9806. Min Range: -2.9806
Max Act: 2.8220. Min Act: -0.1700
Data Index: 2073751 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19