Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8922. Min Act: -0.1700
Data Index: 7502862 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8610. Min Act: -0.1700
Data Index: 5249633 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7985. Min Act: -0.1700
Data Index: 4357640 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7985. Min Act: -0.1700
Data Index: 1000583 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 3691203 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 7344345 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 6873679 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 5279742 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 3897998 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7985. Min Act: -0.1700
Data Index: 4954719 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 4150085 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 5034639 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 7839655 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7047. Min Act: -0.1700
Data Index: 3181747 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 31491 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 50128 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 897421 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 459493 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7360. Min Act: -0.1700
Data Index: 4781946 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7047. Min Act: -0.1700
Data Index: 4147955 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19