Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.6641. Min Act: -0.1700
Data Index: 3745469 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.6641. Min Act: -0.1700
Data Index: 6467826 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.5078. Min Act: -0.1700
Data Index: 1986903 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.4766. Min Act: -0.1700
Data Index: 5422345 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.4766. Min Act: -0.1700
Data Index: 1821844 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.3516. Min Act: -0.1700
Data Index: 5137616 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.3203. Min Act: -0.1700
Data Index: 3548408 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2891. Min Act: -0.1700
Data Index: 579557 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2578. Min Act: -0.1700
Data Index: 3793065 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.3203. Min Act: -0.1700
Data Index: 1184076 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2578. Min Act: -0.1700
Data Index: 7923507 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.2266. Min Act: -0.1700
Data Index: 8062463 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1953. Min Act: -0.1700
Data Index: 1883910 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1641. Min Act: -0.1700
Data Index: 5243847 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1328. Min Act: -0.1700
Data Index: 4594989 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1328. Min Act: -0.1700
Data Index: 5222035 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1016. Min Act: -0.1700
Data Index: 5006969 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1016. Min Act: -0.1700
Data Index: 1635620 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3239406 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6641. Min Range: -7.6641
Max Act: 7.1016. Min Act: -0.1700
Data Index: 7888843 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19