Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.6061. Min Act: -0.1700
Data Index: 6765889 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3560. Min Act: -0.1700
Data Index: 5534271 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.2935. Min Act: -0.1700
Data Index: 8413892 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.0122. Min Act: -0.1700
Data Index: 292690 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.0122. Min Act: -0.1700
Data Index: 6813638 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.0435. Min Act: -0.1700
Data Index: 3710731 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9810. Min Act: -0.1700
Data Index: 3128397 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9028. Min Act: -0.1700
Data Index: 2263853 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9810. Min Act: -0.1700
Data Index: 8728164 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9497. Min Act: -0.1700
Data Index: 6260071 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9497. Min Act: -0.1700
Data Index: 465712 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9341. Min Act: -0.1700
Data Index: 2841049 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.9185. Min Act: -0.1700
Data Index: 8094372 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8716. Min Act: -0.1700
Data Index: 4068474 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8247. Min Act: -0.1700
Data Index: 3559599 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8716. Min Act: -0.1700
Data Index: 3513879 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8559. Min Act: -0.1700
Data Index: 422787 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8559. Min Act: -0.1700
Data Index: 3069459 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.7934. Min Act: -0.1700
Data Index: 1256482 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6061. Min Range: -4.6061
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5011326 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19