Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.7225. Min Act: -0.1700
Data Index: 3563849 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.5975. Min Act: -0.1700
Data Index: 8700542 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.4725. Min Act: -0.1700
Data Index: 1234459 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.4725. Min Act: -0.1700
Data Index: 1442034 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.4100. Min Act: -0.1700
Data Index: 1457812 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.4100. Min Act: -0.1700
Data Index: 4255027 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.3475. Min Act: -0.1700
Data Index: 7912932 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2850. Min Act: -0.1700
Data Index: 5586061 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2850. Min Act: -0.1700
Data Index: 7769984 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2850. Min Act: -0.1700
Data Index: 8593957 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2850. Min Act: -0.1700
Data Index: 367615 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2850. Min Act: -0.1700
Data Index: 5378914 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2225. Min Act: -0.1700
Data Index: 8411348 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.1600. Min Act: -0.1700
Data Index: 3647315 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2225. Min Act: -0.1700
Data Index: 7078197 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.2225. Min Act: -0.1700
Data Index: 7682947 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.1600. Min Act: -0.1700
Data Index: 2878497 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.1600. Min Act: -0.1700
Data Index: 2122237 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.1600. Min Act: -0.1700
Data Index: 2070173 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7225. Min Range: -8.7225
Max Act: 8.1600. Min Act: -0.1700
Data Index: 6019363 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19