Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.3267. Min Act: -0.1700
Data Index: 3675636 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.3267. Min Act: -0.1700
Data Index: 2928319 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.3267. Min Act: -0.1700
Data Index: 6147891 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.1704. Min Act: -0.1700
Data Index: 5390860 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.1392. Min Act: -0.1700
Data Index: 5310188 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.1704. Min Act: -0.1700
Data Index: 7333726 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.1079. Min Act: -0.1700
Data Index: 598616 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.0767. Min Act: -0.1700
Data Index: 2000471 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.0142. Min Act: -0.1700
Data Index: 7016907 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.0142. Min Act: -0.1700
Data Index: 7292638 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.0142. Min Act: -0.1700
Data Index: 3675640 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3267. Min Range: -6.3267
Max Act: 6.0142. Min Act: -0.1700
Data Index: 6660448 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9829. Min Act: -0.1700
Data Index: 4042041 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9829. Min Act: -0.1700
Data Index: 1245031 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3745523 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9517. Min Act: -0.1700
Data Index: 8443832 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9829. Min Act: -0.1700
Data Index: 7288970 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9517. Min Act: -0.1700
Data Index: 600034 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9517. Min Act: -0.1700
Data Index: 1707911 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3267. Min Range: -6.3267
Max Act: 5.9204. Min Act: -0.1700
Data Index: 3691656 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19