Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.9509. Min Act: -0.1700
Data Index: 382245 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.9193. Min Act: -0.1700
Data Index: 3080907 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.8717. Min Act: -0.1700
Data Index: 8472219 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.8081. Min Act: -0.1700
Data Index: 3510896 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 8430229 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 5508909 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 246540 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7603. Min Act: -0.1700
Data Index: 8807468 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 6673539 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 601473 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 3423775 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 39674 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7124. Min Act: -0.1700
Data Index: 1476918 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 6051149 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 5754439 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7443. Min Act: -0.1700
Data Index: 2997793 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 6208685 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7284. Min Act: -0.1700
Data Index: 8750987 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7603. Min Act: -0.1700
Data Index: 7632333 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9509. Min Range: -2.9509
Max Act: 2.7124. Min Act: -0.1700
Data Index: 3179351 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19