Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.7203. Min Act: -0.1700
Data Index: 945311 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5641. Min Act: -0.1700
Data Index: 7463569 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.3453. Min Act: -0.1700
Data Index: 7133885 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.2515. Min Act: -0.1700
Data Index: 5889381 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.1890. Min Act: -0.1700
Data Index: 538713 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.1890. Min Act: -0.1700
Data Index: 5917053 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.1890. Min Act: -0.1700
Data Index: 1038603 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.1578. Min Act: -0.1700
Data Index: 6612801 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0953. Min Act: -0.1700
Data Index: 4891033 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.1265. Min Act: -0.1700
Data Index: 3913796 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0640. Min Act: -0.1700
Data Index: 759375 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0640. Min Act: -0.1700
Data Index: 6137666 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0328. Min Act: -0.1700
Data Index: 1928504 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0328. Min Act: -0.1700
Data Index: 7776696 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0015. Min Act: -0.1700
Data Index: 5917063 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1494126 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7203. Min Range: -4.7203
Max Act: 3.9702. Min Act: -0.1700
Data Index: 3548356 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7203. Min Range: -4.7203
Max Act: 3.9702. Min Act: -0.1700
Data Index: 3747183 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7203. Min Range: -4.7203
Max Act: 3.9702. Min Act: -0.1700
Data Index: 8408842 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7203. Min Range: -4.7203
Max Act: 3.9702. Min Act: -0.1700
Data Index: 5678063 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19