Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.7086. Min Act: -0.1700
Data Index: 4174534 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.6926. Min Act: -0.1700
Data Index: 4769262 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.6606. Min Act: -0.1700
Data Index: 6847325 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.6606. Min Act: -0.1700
Data Index: 7261303 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.6285. Min Act: -0.1700
Data Index: 4279860 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.6124. Min Act: -0.1700
Data Index: 3418848 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5963. Min Act: -0.1700
Data Index: 5748907 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5802. Min Act: -0.1700
Data Index: 8467422 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5641. Min Act: -0.1700
Data Index: 6991115 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5963. Min Act: -0.1700
Data Index: 815931 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5802. Min Act: -0.1700
Data Index: 1079573 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5802. Min Act: -0.1700
Data Index: 5392030 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5802. Min Act: -0.1700
Data Index: 2073161 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5641. Min Act: -0.1700
Data Index: 756760 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5641. Min Act: -0.1700
Data Index: 3386955 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5641. Min Act: -0.1700
Data Index: 741457 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5641. Min Act: -0.1700
Data Index: 6954203 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5802. Min Act: -0.1700
Data Index: 3863854 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5480. Min Act: -0.1700
Data Index: 3801424 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7086. Min Range: -2.7086
Max Act: 2.5480. Min Act: -0.1700
Data Index: 4153703 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19