Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1720. Min Range: -4.1720
Max Act: 4.1720. Min Act: -0.1700
Data Index: 4037040 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1720. Min Range: -4.1720
Max Act: 4.0001. Min Act: -0.1700
Data Index: 4697678 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9845. Min Act: -0.1700
Data Index: 1327271 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9845. Min Act: -0.1700
Data Index: 7754530 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9688. Min Act: -0.1700
Data Index: 2270373 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9688. Min Act: -0.1700
Data Index: 8409292 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9688. Min Act: -0.1700
Data Index: 2773804 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9219. Min Act: -0.1700
Data Index: 3333747 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8907. Min Act: -0.1700
Data Index: 6423350 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8907. Min Act: -0.1700
Data Index: 3401953 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8750. Min Act: -0.1700
Data Index: 8742646 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.9063. Min Act: -0.1700
Data Index: 957183 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8750. Min Act: -0.1700
Data Index: 6898296 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8594. Min Act: -0.1700
Data Index: 8278870 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8750. Min Act: -0.1700
Data Index: 8538720 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8438. Min Act: -0.1700
Data Index: 5610321 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8281. Min Act: -0.1700
Data Index: 899207 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8438. Min Act: -0.1700
Data Index: 6856339 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8438. Min Act: -0.1700
Data Index: 2654303 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1720. Min Range: -4.1720
Max Act: 3.8594. Min Act: -0.1700
Data Index: 410708 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19