Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 821 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.7719. Min Act: -0.1700
Data Index: 5805396 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.5532. Min Act: -0.1700
Data Index: 2585725 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.2407. Min Act: -0.1700
Data Index: 7091884 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.1782. Min Act: -0.1700
Data Index: 8504875 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.1469. Min Act: -0.1700
Data Index: 2612330 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.0219. Min Act: -0.1700
Data Index: 3822850 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.0844. Min Act: -0.1700
Data Index: 4615338 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7719. Min Range: -6.7719
Max Act: 6.0219. Min Act: -0.1700
Data Index: 3090900 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9282. Min Act: -0.1700
Data Index: 2314746 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9594. Min Act: -0.1700
Data Index: 222750 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9594. Min Act: -0.1700
Data Index: 3328814 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9282. Min Act: -0.1700
Data Index: 3999681 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8969. Min Act: -0.1700
Data Index: 1948528 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9594. Min Act: -0.1700
Data Index: 4225172 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8969. Min Act: -0.1700
Data Index: 171158 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.9282. Min Act: -0.1700
Data Index: 4940303 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8969. Min Act: -0.1700
Data Index: 7067903 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8969. Min Act: -0.1700
Data Index: 3425575 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4531675 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7719. Min Range: -6.7719
Max Act: 5.8344. Min Act: -0.1700
Data Index: 6310773 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19