Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2110 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.2566. Min Act: -0.1700
Data Index: 8429891 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.2253. Min Act: -0.1700
Data Index: 2004390 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1941. Min Act: -0.1700
Data Index: 5964882 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1941. Min Act: -0.1700
Data Index: 1056944 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1628. Min Act: -0.1700
Data Index: 8244235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1315. Min Act: -0.1700
Data Index: 7747866 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1628. Min Act: -0.1700
Data Index: 3204046 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1315. Min Act: -0.1700
Data Index: 5315403 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1003. Min Act: -0.1700
Data Index: 8663082 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1315. Min Act: -0.1700
Data Index: 8408549 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0690. Min Act: -0.1700
Data Index: 5943179 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0690. Min Act: -0.1700
Data Index: 2577730 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.1003. Min Act: -0.1700
Data Index: 2134496 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0690. Min Act: -0.1700
Data Index: 547056 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0690. Min Act: -0.1700
Data Index: 2935012 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0690. Min Act: -0.1700
Data Index: 6879815 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0065. Min Act: -0.1700
Data Index: 1517577 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0378. Min Act: -0.1700
Data Index: 2205702 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0378. Min Act: -0.1700
Data Index: 5315405 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2566. Min Range: -4.2566
Max Act: 4.0065. Min Act: -0.1700
Data Index: 4397170 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19