Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.6080. Min Act: -0.1700
Data Index: 6060698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.6080. Min Act: -0.1700
Data Index: 4096504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 2730387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 8794733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 8319503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 4204898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 7177418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1658055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 3723814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 3635939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 3574216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1325280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 5724410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1285263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 295726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 3164072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1137545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 5032713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1915008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6080. Min Range: -2.6080
Max Act: 2.5435. Min Act: -0.1700
Data Index: 440101 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19