Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0872. Min Range: -5.0872
Max Act: 5.0872. Min Act: -0.1700
Data Index: 2210570 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0872. Min Range: -5.0872
Max Act: 5.0560. Min Act: -0.1700
Data Index: 2517777 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.9310. Min Act: -0.1700
Data Index: 453396 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.8997. Min Act: -0.1700
Data Index: 6375534 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.8372. Min Act: -0.1700
Data Index: 6997590 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.8060. Min Act: -0.1700
Data Index: 5766564 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7435. Min Act: -0.1700
Data Index: 1565915 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7435. Min Act: -0.1700
Data Index: 60454 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7122. Min Act: -0.1700
Data Index: 2542487 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7435. Min Act: -0.1700
Data Index: 3419752 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7435. Min Act: -0.1700
Data Index: 1871647 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 5206950 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 6365529 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.7122. Min Act: -0.1700
Data Index: 8202980 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6497. Min Act: -0.1700
Data Index: 5976825 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 5643745 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6497. Min Act: -0.1700
Data Index: 1400281 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 4073812 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 2804905 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0872. Min Range: -5.0872
Max Act: 4.6810. Min Act: -0.1700
Data Index: 99690 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19