Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 229 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0579. Min Range: -6.0579
Max Act: 6.0579. Min Act: -0.1700
Data Index: 5135311 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6787368 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.9016. Min Act: -0.1700
Data Index: 4750960 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.8704. Min Act: -0.1700
Data Index: 7587030 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.7766. Min Act: -0.1700
Data Index: 1049963 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.7454. Min Act: -0.1700
Data Index: 6217575 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.7454. Min Act: -0.1700
Data Index: 6245695 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.7454. Min Act: -0.1700
Data Index: 2635127 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.7141. Min Act: -0.1700
Data Index: 28472 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.6829. Min Act: -0.1700
Data Index: 5934542 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.6829. Min Act: -0.1700
Data Index: 6508017 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3312772 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4690554 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 8200686 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 7992217 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7237317 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 6983040 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 1454499 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 771120 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0579. Min Range: -6.0579
Max Act: 5.5891. Min Act: -0.1700
Data Index: 3732842 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19