Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0284. Min Range: -4.0284
Max Act: 4.0284. Min Act: -0.1700
Data Index: 302365 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.9971. Min Act: -0.1700
Data Index: 3044483 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.8877. Min Act: -0.1700
Data Index: 3605523 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.8721. Min Act: -0.1700
Data Index: 2936898 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.8252. Min Act: -0.1700
Data Index: 6065077 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.8095. Min Act: -0.1700
Data Index: 4565827 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.7470. Min Act: -0.1700
Data Index: 638119 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.7783. Min Act: -0.1700
Data Index: 7140819 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.7626. Min Act: -0.1700
Data Index: 7999530 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.7157. Min Act: -0.1700
Data Index: 5842032 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6844. Min Act: -0.1700
Data Index: 983337 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6844. Min Act: -0.1700
Data Index: 3904269 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6688. Min Act: -0.1700
Data Index: 89255 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6531. Min Act: -0.1700
Data Index: 896575 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6531. Min Act: -0.1700
Data Index: 8554080 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6375. Min Act: -0.1700
Data Index: 3557780 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6688. Min Act: -0.1700
Data Index: 5688338 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6531. Min Act: -0.1700
Data Index: 3508657 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6375. Min Act: -0.1700
Data Index: 5218448 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0284. Min Range: -4.0284
Max Act: 3.6218. Min Act: -0.1700
Data Index: 1676839 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19