Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1328 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.4509. Min Act: -0.1700
Data Index: 6105827 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.2634. Min Act: -0.1700
Data Index: 3508604 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.2634. Min Act: -0.1700
Data Index: 3366715 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.2321. Min Act: -0.1700
Data Index: 7285128 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.2009. Min Act: -0.1700
Data Index: 1860069 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1696. Min Act: -0.1700
Data Index: 551826 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1384. Min Act: -0.1700
Data Index: 1036622 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1071. Min Act: -0.1700
Data Index: 5283602 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1384. Min Act: -0.1700
Data Index: 2666306 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1384. Min Act: -0.1700
Data Index: 374023 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0759. Min Act: -0.1700
Data Index: 4409873 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1696. Min Act: -0.1700
Data Index: 1594298 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.2009. Min Act: -0.1700
Data Index: 4213211 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0759. Min Act: -0.1700
Data Index: 7507220 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.1071. Min Act: -0.1700
Data Index: 3712193 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0759. Min Act: -0.1700
Data Index: 1429609 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0446. Min Act: -0.1700
Data Index: 846601 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0759. Min Act: -0.1700
Data Index: 1446347 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4509. Min Range: -6.4509
Max Act: 5.9509. Min Act: -0.1700
Data Index: 1246423 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4509. Min Range: -6.4509
Max Act: 6.0134. Min Act: -0.1700
Data Index: 6558535 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19