Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3454. Min Act: -0.1700
Data Index: 3387901 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3141. Min Act: -0.1700
Data Index: 7435414 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1579. Min Act: -0.1700
Data Index: 2458287 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1891. Min Act: -0.1700
Data Index: 8196677 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0954. Min Act: -0.1700
Data Index: 8239763 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1579. Min Act: -0.1700
Data Index: 8799818 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1266. Min Act: -0.1700
Data Index: 3393074 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0954. Min Act: -0.1700
Data Index: 1845141 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0641. Min Act: -0.1700
Data Index: 1355650 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 2983449 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3454. Min Range: -4.3454
Max Act: 3.9703. Min Act: -0.1700
Data Index: 6930783 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 7127086 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3454. Min Range: -4.3454
Max Act: 3.9703. Min Act: -0.1700
Data Index: 1945180 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3454. Min Range: -4.3454
Max Act: 3.9703. Min Act: -0.1700
Data Index: 6804590 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 4223029 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 5847902 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 732469 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 4901607 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3454. Min Range: -4.3454
Max Act: 3.9703. Min Act: -0.1700
Data Index: 3753637 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3454. Min Range: -4.3454
Max Act: 3.9703. Min Act: -0.1700
Data Index: 1081829 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19