Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.7883. Min Act: -0.1700
Data Index: 7479469 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.3508. Min Act: -0.1700
Data Index: 7163377 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.2258. Min Act: -0.1700
Data Index: 7081728 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.2258. Min Act: -0.1700
Data Index: 4434980 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.1633. Min Act: -0.1700
Data Index: 5916798 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0696. Min Act: -0.1700
Data Index: 5035346 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0696. Min Act: -0.1700
Data Index: 979037 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0383. Min Act: -0.1700
Data Index: 4873697 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0383. Min Act: -0.1700
Data Index: 2788229 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0071. Min Act: -0.1700
Data Index: 5808338 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 5984847 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7883. Min Range: -6.7883
Max Act: 6.0383. Min Act: -0.1700
Data Index: 2595770 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.9446. Min Act: -0.1700
Data Index: 2417104 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.9446. Min Act: -0.1700
Data Index: 116087 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.9133. Min Act: -0.1700
Data Index: 1956646 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.8508. Min Act: -0.1700
Data Index: 2193936 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.8508. Min Act: -0.1700
Data Index: 882850 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.8196. Min Act: -0.1700
Data Index: 2859413 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7307476 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7883. Min Range: -6.7883
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7193310 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19